Excellent. Thought-provoking., 18 May 2008
A very well presented, and extremely well researched effort. Everyone should read this. One star deducted jointly for the shameless (and frequent) promotion of the author's other works, and the sometimes unnecessarily long-winded passages in the book - its still very well done, but this is my own opinion.

I strongly recommend this book, very hard to put down.

Contains some wonderful ideas., 30 Apr 2008
For those of you who don't know, Ray Kurzweil is the man who invented Optical Character Recognition, along with various other pattern-recognition technologies. He is well-versed in what technology is theoretically capable of, and has spent his professional life trying to make it do these things.

I have nothing but good things to say about Ray Kurzweil, and this book in particular. The ideas that he puts forward may seem very optimistic, sometimes verging on techno-fanaticism, but nothing he is saying is negative. If he's right, the human race only has to survive until the 2040s and things will markedly improve.

However excellent I found the technological predictions made in this book, there are two points that brought it down to four stars. First, and a matter I admit is one of personal preference, there were far too many graphs to do with economy and business. This is an American book, so capitalism has to figure somewhere, and he is forgiven. The other point is that some of the speculations he is making are sociological ones and these are far more spurious than any technological speculations. However, they are not fundamental to what he is arguing.

All in all, an excellent, if at times overwhelming, read. I heartily recommend it as an introduction to transhumanism and futurism.

Revelatory, 21 Mar 2008
I discovered this book a couple of years ago. There was a sale at Waterstone's, and I had all but one of the books needed to take advantage of said sale. This took my interest, so I got a hold of it, and thank goodness I did.

I can honestly say that this is the most important non-fiction book I have ever read, and quite possibly one of the most important books period. Whilst I have always sensed something important might be taking place regarding technology, and I have always had a deep love of science and technology, Kurzweil highlights and articulates some incredible and illustrative concepts. I don't agree with everything he says, but the fundaments of the book seem entirely solid. Sometimes this terrifies me, but Kurzweil offers a great deal of hope as well.

Whether you embrace or reject the implications, however, Kurzweil's book makes an extremely imposing case that I have yet to see refuted. Reading it will prepare you for the future, whether that future looks glorious or horrifying to you.

Awesome book, 24 Jan 2008
My heart sank when I got this book. An American book on science that had that many pages must be written by someone who got paid by how many times they were able to repeat themselves. This has been my experience with books much thinner than this. Yet I was quite wrong. There is very little repetition and it is all appropriate. The book is very well written with careful attention given to the order in which ideas are presented. It is an astonishingly wide ranging book and essential reading for anyone who is interested in where technology is taking us. How the author found time to write it, along with perfoming all his other duties beats me. He must be one hell of a guy!
The only thing I take issue with him on, is... no I won't spoil it for you! You can make up your own mind. Just read it!

Excellent. Thought-provoking., 18 May 2008
A very well presented, and extremely well researched effort. Everyone should read this. One star deducted jointly for the shameless (and frequent) promotion of the author's other works, and the sometimes unnecessarily long-winded passages in the book - its still very well done, but this is my own opinion.

I strongly recommend this book, very hard to put down.

Contains some wonderful ideas., 30 Apr 2008
For those of you who don't know, Ray Kurzweil is the man who invented Optical Character Recognition, along with various other pattern-recognition technologies. He is well-versed in what technology is theoretically capable of, and has spent his professional life trying to make it do these things.

I have nothing but good things to say about Ray Kurzweil, and this book in particular. The ideas that he puts forward may seem very optimistic, sometimes verging on techno-fanaticism, but nothing he is saying is negative. If he's right, the human race only has to survive until the 2040s and things will markedly improve.

However excellent I found the technological predictions made in this book, there are two points that brought it down to four stars. First, and a matter I admit is one of personal preference, there were far too many graphs to do with economy and business. This is an American book, so capitalism has to figure somewhere, and he is forgiven. The other point is that some of the speculations he is making are sociological ones and these are far more spurious than any technological speculations. However, they are not fundamental to what he is arguing.

All in all, an excellent, if at times overwhelming, read. I heartily recommend it as an introduction to transhumanism and futurism.

Revelatory, 21 Mar 2008
I discovered this book a couple of years ago. There was a sale at Waterstone's, and I had all but one of the books needed to take advantage of said sale. This took my interest, so I got a hold of it, and thank goodness I did.

I can honestly say that this is the most important non-fiction book I have ever read, and quite possibly one of the most important books period. Whilst I have always sensed something important might be taking place regarding technology, and I have always had a deep love of science and technology, Kurzweil highlights and articulates some incredible and illustrative concepts. I don't agree with everything he says, but the fundaments of the book seem entirely solid. Sometimes this terrifies me, but Kurzweil offers a great deal of hope as well.

Whether you embrace or reject the implications, however, Kurzweil's book makes an extremely imposing case that I have yet to see refuted. Reading it will prepare you for the future, whether that future looks glorious or horrifying to you.

Awesome book, 24 Jan 2008
My heart sank when I got this book. An American book on science that had that many pages must be written by someone who got paid by how many times they were able to repeat themselves. This has been my experience with books much thinner than this. Yet I was quite wrong. There is very little repetition and it is all appropriate. The book is very well written with careful attention given to the order in which ideas are presented. It is an astonishingly wide ranging book and essential reading for anyone who is interested in where technology is taking us. How the author found time to write it, along with perfoming all his other duties beats me. He must be one hell of a guy!
The only thing I take issue with him on, is... no I won't spoil it for you! You can make up your own mind. Just read it!

good reference reference book but..., 11 Jul 2007
..don't like the writing style. Fewer equations and more explanations would have made it a better book.



Great insights, but a hard read, 14 Jun 2007
This new book by Chris Bishop covers most areas of pattern recognition quite exhaustively. The author is an expert, this is evidenced by the excellent insights he gives into the complex math behind the machine learning algorithms. I have worked for quite some time with neural networks and have had coursework in linear algebra, probability and regression analysis, and hence found some of the stuff in the book quite illuminating.

But that said, I must point out that the book is very math heavy. Inspite of my considerable background in the area of neural networks, I still was struggling with the equations. This is certainly not the book that can teach one things from the ground up, and thats why I would give it only 3 stars. I am new to kernels, and I am finding the relevant chapters quite confusing. For those who want to build powerful machine learning solutions to their problems, I am sorry but they will have to look elsewhere. This book cant help you build an application, another serious drawback in my opinion. The intended audience for this book I guess are PhD students/researchers who are working with the math related aspects of machine learning, and not undergraduates or working professionals who want to write machine learning code for their applications/projects.

Best book of its kind I have found, 24 Mar 2007
Bishop does an excellent job of helping the reader visualize what is going on in the problems and techniques he describes, emphasizing an intuitive grasp of the issues without sacrificing mathematical rigour. The writing is clear and the production is excellent. Strongly recommended both for anyone serious about getting into machine learning and for those already working in it.


Excellent book, 29 Jan 2007
As a newbie to pattern recognition I found this book very helpful. It is the clearest book I ever read! Accompanying examples and material are very illuminating. I particularly appreciated the gradual introduction of key concepts, often accompanied with practical examples and stimulating exercises.

Excellent. Thought-provoking., 18 May 2008
A very well presented, and extremely well researched effort. Everyone should read this. One star deducted jointly for the shameless (and frequent) promotion of the author's other works, and the sometimes unnecessarily long-winded passages in the book - its still very well done, but this is my own opinion.

I strongly recommend this book, very hard to put down.

Contains some wonderful ideas., 30 Apr 2008
For those of you who don't know, Ray Kurzweil is the man who invented Optical Character Recognition, along with various other pattern-recognition technologies. He is well-versed in what technology is theoretically capable of, and has spent his professional life trying to make it do these things.

I have nothing but good things to say about Ray Kurzweil, and this book in particular. The ideas that he puts forward may seem very optimistic, sometimes verging on techno-fanaticism, but nothing he is saying is negative. If he's right, the human race only has to survive until the 2040s and things will markedly improve.

However excellent I found the technological predictions made in this book, there are two points that brought it down to four stars. First, and a matter I admit is one of personal preference, there were far too many graphs to do with economy and business. This is an American book, so capitalism has to figure somewhere, and he is forgiven. The other point is that some of the speculations he is making are sociological ones and these are far more spurious than any technological speculations. However, they are not fundamental to what he is arguing.

All in all, an excellent, if at times overwhelming, read. I heartily recommend it as an introduction to transhumanism and futurism.

Revelatory, 21 Mar 2008
I discovered this book a couple of years ago. There was a sale at Waterstone's, and I had all but one of the books needed to take advantage of said sale. This took my interest, so I got a hold of it, and thank goodness I did.

I can honestly say that this is the most important non-fiction book I have ever read, and quite possibly one of the most important books period. Whilst I have always sensed something important might be taking place regarding technology, and I have always had a deep love of science and technology, Kurzweil highlights and articulates some incredible and illustrative concepts. I don't agree with everything he says, but the fundaments of the book seem entirely solid. Sometimes this terrifies me, but Kurzweil offers a great deal of hope as well.

Whether you embrace or reject the implications, however, Kurzweil's book makes an extremely imposing case that I have yet to see refuted. Reading it will prepare you for the future, whether that future looks glorious or horrifying to you.

Awesome book, 24 Jan 2008
My heart sank when I got this book. An American book on science that had that many pages must be written by someone who got paid by how many times they were able to repeat themselves. This has been my experience with books much thinner than this. Yet I was quite wrong. There is very little repetition and it is all appropriate. The book is very well written with careful attention given to the order in which ideas are presented. It is an astonishingly wide ranging book and essential reading for anyone who is interested in where technology is taking us. How the author found time to write it, along with perfoming all his other duties beats me. He must be one hell of a guy!
The only thing I take issue with him on, is... no I won't spoil it for you! You can make up your own mind. Just read it!

good reference reference book but..., 11 Jul 2007
..don't like the writing style. Fewer equations and more explanations would have made it a better book.



Great insights, but a hard read, 14 Jun 2007
This new book by Chris Bishop covers most areas of pattern recognition quite exhaustively. The author is an expert, this is evidenced by the excellent insights he gives into the complex math behind the machine learning algorithms. I have worked for quite some time with neural networks and have had coursework in linear algebra, probability and regression analysis, and hence found some of the stuff in the book quite illuminating.

But that said, I must point out that the book is very math heavy. Inspite of my considerable background in the area of neural networks, I still was struggling with the equations. This is certainly not the book that can teach one things from the ground up, and thats why I would give it only 3 stars. I am new to kernels, and I am finding the relevant chapters quite confusing. For those who want to build powerful machine learning solutions to their problems, I am sorry but they will have to look elsewhere. This book cant help you build an application, another serious drawback in my opinion. The intended audience for this book I guess are PhD students/researchers who are working with the math related aspects of machine learning, and not undergraduates or working professionals who want to write machine learning code for their applications/projects.

Best book of its kind I have found, 24 Mar 2007
Bishop does an excellent job of helping the reader visualize what is going on in the problems and techniques he describes, emphasizing an intuitive grasp of the issues without sacrificing mathematical rigour. The writing is clear and the production is excellent. Strongly recommended both for anyone serious about getting into machine learning and for those already working in it.


Excellent book, 29 Jan 2007
As a newbie to pattern recognition I found this book very helpful. It is the clearest book I ever read! Accompanying examples and material are very illuminating. I particularly appreciated the gradual introduction of key concepts, often accompanied with practical examples and stimulating exercises.

Great tour of physics, not sure about the metaphysics, 15 Aug 2008
I give this book five stars cos it occupies, along with Barrow and Tipler's The Anthropic Cosmological Principle (Oxford Paperbacks) a niche that nothing else quite does. It is on the furthest edge of popular science writing before you penetrate into the realm of the specialist. So for a person like me with undergraduate maths it gave me a lot of information without intolerable effort. It was tough going but very worthwhile. For anyone with less than A-level (I mean 70's A-level) maths though, I'd stick with the books with no equations, like the very popular A Brief History of Time: From the Big Bang to Black Holes, which I rate more as a human interest story than as an introduction to any actual cosmology.

As for Penrose's conjectures about the mental. Well, his ideas have been around for a while now and as far as I can tell have not led us to anything new. He exhibits the common fuzziness of the day, that is only really now getting tightened up on in the Philosophy of Mind literature, of conflating the problem of mentation, i.e. what goes on in the mind of a mathematician when she's having a great insight, with the problem of consciousness, i.e. what is it? They are both profound and mysterious problems but they are not the same problem, and not even necessarily related. I can still see a space for how quantum mechanical, i.e. truly random, processes might get exploited in pruning decision trees when searching a problem space, i.e. with respect the mentation problem. But how quantum randomness might contribute to consciousness seems more problematic.

The most incisive contribution to the question of consciousness I'm aware of right now is Edelman & Tononi's A Universe of Consciousness How Matter Becomes Imagination.

But this book is great for the physics, and certainly at the limits of what someone of my educational background can indulge in as a spare time activity. Penrose's next book on this topic Shadows of the Mind: A Search for the Missing Science of Consciousness was more mathematically rigorous and lost me pretty well straight away.

Skip this, 11 Aug 2008
The one redeeming feature this book had was its overview of theoretical physics. The chapters bookending the good bit were a complete nonsense. Penrose has now produced another, more in-depth and quite superb, version of his take on physics in The Road to Reality, thereby obviating the need for this title.

Stylistic difficulties mask an outstanding book, 30 Dec 2007
Penrose does not shrink from the difficult when trying to explain the problems he's obsessed about. This is one of the best books on the subject (the subject in question being "What's it all about, really, when you come to think of it?"), and I can't think of anyone else who's treading the same ground in the same way (Hawking's rather more specialised and abstruse, Greene centres mainly on the details of the physics and Hofstadter's more into the logic and philosophy).

However, I have difficulty with Penrose's style, and find he can be a bit difficult to follow sometimes. Having said that, it's no easy task to put all these concepts into plain prose. I know I couldn't do it.

Entertaining and Mathematically Advanced, 21 Jul 2006
I found this book stimulating and entertaining in equal measure. It looks at the questions such as -- if we had enough information, we could predict absolutely everything, or not? Is the human mind simply a machine (for example a computer)? Can we actually be transported Star-trek style or not? Are we (including our memories) just a collection of atoms that could be reconstituted?

In answering these questions Penrose embarks on a tour of the mathematical concepts and theories that underpin our understanding of the Universe.

There seems to be much more maths than is really needed, and there is a lot of theory (The book runs to over 500 pages after all). You will also need advanced A level maths to cope (on the basis that I just coped, and that's the level of maths I reached).

Entertaining and enjoyable IF you are interested in Maths. If you are not, stay away.

Misleading Title, 13 May 2003
The book digreses too far from its title with long detailed coverage of mathematical proofs and descriptions of quantum mechanics. The material could be bypassed or expressed more succingtly. The final conclusion is rather weak: somehow thanks to the hard or impossible to predict nature of sub-atomic events: free-will and human nature will still survive beyond the reach of computing.

Excellent. Thought-provoking., 18 May 2008
A very well presented, and extremely well researched effort. Everyone should read this. One star deducted jointly for the shameless (and frequent) promotion of the author's other works, and the sometimes unnecessarily long-winded passages in the book - its still very well done, but this is my own opinion.

I strongly recommend this book, very hard to put down.

Contains some wonderful ideas., 30 Apr 2008
For those of you who don't know, Ray Kurzweil is the man who invented Optical Character Recognition, along with various other pattern-recognition technologies. He is well-versed in what technology is theoretically capable of, and has spent his professional life trying to make it do these things.

I have nothing but good things to say about Ray Kurzweil, and this book in particular. The ideas that he puts forward may seem very optimistic, sometimes verging on techno-fanaticism, but nothing he is saying is negative. If he's right, the human race only has to survive until the 2040s and things will markedly improve.

However excellent I found the technological predictions made in this book, there are two points that brought it down to four stars. First, and a matter I admit is one of personal preference, there were far too many graphs to do with economy and business. This is an American book, so capitalism has to figure somewhere, and he is forgiven. The other point is that some of the speculations he is making are sociological ones and these are far more spurious than any technological speculations. However, they are not fundamental to what he is arguing.

All in all, an excellent, if at times overwhelming, read. I heartily recommend it as an introduction to transhumanism and futurism.

Revelatory, 21 Mar 2008
I discovered this book a couple of years ago. There was a sale at Waterstone's, and I had all but one of the books needed to take advantage of said sale. This took my interest, so I got a hold of it, and thank goodness I did.

I can honestly say that this is the most important non-fiction book I have ever read, and quite possibly one of the most important books period. Whilst I have always sensed something important might be taking place regarding technology, and I have always had a deep love of science and technology, Kurzweil highlights and articulates some incredible and illustrative concepts. I don't agree with everything he says, but the fundaments of the book seem entirely solid. Sometimes this terrifies me, but Kurzweil offers a great deal of hope as well.

Whether you embrace or reject the implications, however, Kurzweil's book makes an extremely imposing case that I have yet to see refuted. Reading it will prepare you for the future, whether that future looks glorious or horrifying to you.

Awesome book, 24 Jan 2008
My heart sank when I got this book. An American book on science that had that many pages must be written by someone who got paid by how many times they were able to repeat themselves. This has been my experience with books much thinner than this. Yet I was quite wrong. There is very little repetition and it is all appropriate. The book is very well written with careful attention given to the order in which ideas are presented. It is an astonishingly wide ranging book and essential reading for anyone who is interested in where technology is taking us. How the author found time to write it, along with perfoming all his other duties beats me. He must be one hell of a guy!
The only thing I take issue with him on, is... no I won't spoil it for you! You can make up your own mind. Just read it!

good reference reference book but..., 11 Jul 2007
..don't like the writing style. Fewer equations and more explanations would have made it a better book.



Great insights, but a hard read, 14 Jun 2007
This new book by Chris Bishop covers most areas of pattern recognition quite exhaustively. The author is an expert, this is evidenced by the excellent insights he gives into the complex math behind the machine learning algorithms. I have worked for quite some time with neural networks and have had coursework in linear algebra, probability and regression analysis, and hence found some of the stuff in the book quite illuminating.

But that said, I must point out that the book is very math heavy. Inspite of my considerable background in the area of neural networks, I still was struggling with the equations. This is certainly not the book that can teach one things from the ground up, and thats why I would give it only 3 stars. I am new to kernels, and I am finding the relevant chapters quite confusing. For those who want to build powerful machine learning solutions to their problems, I am sorry but they will have to look elsewhere. This book cant help you build an application, another serious drawback in my opinion. The intended audience for this book I guess are PhD students/researchers who are working with the math related aspects of machine learning, and not undergraduates or working professionals who want to write machine learning code for their applications/projects.

Best book of its kind I have found, 24 Mar 2007
Bishop does an excellent job of helping the reader visualize what is going on in the problems and techniques he describes, emphasizing an intuitive grasp of the issues without sacrificing mathematical rigour. The writing is clear and the production is excellent. Strongly recommended both for anyone serious about getting into machine learning and for those already working in it.


Excellent book, 29 Jan 2007
As a newbie to pattern recognition I found this book very helpful. It is the clearest book I ever read! Accompanying examples and material are very illuminating. I particularly appreciated the gradual introduction of key concepts, often accompanied with practical examples and stimulating exercises.

Great tour of physics, not sure about the metaphysics, 15 Aug 2008
I give this book five stars cos it occupies, along with Barrow and Tipler's The Anthropic Cosmological Principle (Oxford Paperbacks) a niche that nothing else quite does. It is on the furthest edge of popular science writing before you penetrate into the realm of the specialist. So for a person like me with undergraduate maths it gave me a lot of information without intolerable effort. It was tough going but very worthwhile. For anyone with less than A-level (I mean 70's A-level) maths though, I'd stick with the books with no equations, like the very popular A Brief History of Time: From the Big Bang to Black Holes, which I rate more as a human interest story than as an introduction to any actual cosmology.

As for Penrose's conjectures about the mental. Well, his ideas have been around for a while now and as far as I can tell have not led us to anything new. He exhibits the common fuzziness of the day, that is only really now getting tightened up on in the Philosophy of Mind literature, of conflating the problem of mentation, i.e. what goes on in the mind of a mathematician when she's having a great insight, with the problem of consciousness, i.e. what is it? They are both profound and mysterious problems but they are not the same problem, and not even necessarily related. I can still see a space for how quantum mechanical, i.e. truly random, processes might get exploited in pruning decision trees when searching a problem space, i.e. with respect the mentation problem. But how quantum randomness might contribute to consciousness seems more problematic.

The most incisive contribution to the question of consciousness I'm aware of right now is Edelman & Tononi's A Universe of Consciousness How Matter Becomes Imagination.

But this book is great for the physics, and certainly at the limits of what someone of my educational background can indulge in as a spare time activity. Penrose's next book on this topic Shadows of the Mind: A Search for the Missing Science of Consciousness was more mathematically rigorous and lost me pretty well straight away.

Skip this, 11 Aug 2008
The one redeeming feature this book had was its overview of theoretical physics. The chapters bookending the good bit were a complete nonsense. Penrose has now produced another, more in-depth and quite superb, version of his take on physics in The Road to Reality, thereby obviating the need for this title.

Stylistic difficulties mask an outstanding book, 30 Dec 2007
Penrose does not shrink from the difficult when trying to explain the problems he's obsessed about. This is one of the best books on the subject (the subject in question being "What's it all about, really, when you come to think of it?"), and I can't think of anyone else who's treading the same ground in the same way (Hawking's rather more specialised and abstruse, Greene centres mainly on the details of the physics and Hofstadter's more into the logic and philosophy).

However, I have difficulty with Penrose's style, and find he can be a bit difficult to follow sometimes. Having said that, it's no easy task to put all these concepts into plain prose. I know I couldn't do it.

Entertaining and Mathematically Advanced, 21 Jul 2006
I found this book stimulating and entertaining in equal measure. It looks at the questions such as -- if we had enough information, we could predict absolutely everything, or not? Is the human mind simply a machine (for example a computer)? Can we actually be transported Star-trek style or not? Are we (including our memories) just a collection of atoms that could be reconstituted?

In answering these questions Penrose embarks on a tour of the mathematical concepts and theories that underpin our understanding of the Universe.

There seems to be much more maths than is really needed, and there is a lot of theory (The book runs to over 500 pages after all). You will also need advanced A level maths to cope (on the basis that I just coped, and that's the level of maths I reached).

Entertaining and enjoyable IF you are interested in Maths. If you are not, stay away.

Misleading Title, 13 May 2003
The book digreses too far from its title with long detailed coverage of mathematical proofs and descriptions of quantum mechanics. The material could be bypassed or expressed more succingtly. The final conclusion is rather weak: somehow thanks to the hard or impossible to predict nature of sub-atomic events: free-will and human nature will still survive beyond the reach of computing.

Revised and ready to lead you down a good path, 21 May 2006
Having read the first edition, the authors earn the extra rating because they've managed to improve on their work and practical WEKA resource offering. Without a doubt, an essential read for people who are both new and experienced in the fields of data mining, descriptive & predictive analytics or state & behavioural modelling.

The volume of material on the market today is still quite limited and in the gap between the first and second edition of this book, quite a lot has actually changed in the field. In my view, book content has only marginally progressed with the times, perhaps in favour of attempting to attract and activate new members, practictioners and commercially oriented researchers to the fore of data mining. It's a bold step to evolve material as the field evolves; those breaking new ground in this area should be more visible and offered greater support.

I believe that there is room in the market now for some revised materials covering anomalised commercial implementations of Advanced Data Mining & AI Concepts. A small community of authors could plug this gap really well.

Excellent. Thought-provoking., 18 May 2008
A very well presented, and extremely well researched effort. Everyone should read this. One star deducted jointly for the shameless (and frequent) promotion of the author's other works, and the sometimes unnecessarily long-winded passages in the book - its still very well done, but this is my own opinion.

I strongly recommend this book, very hard to put down.

Contains some wonderful ideas., 30 Apr 2008
For those of you who don't know, Ray Kurzweil is the man who invented Optical Character Recognition, along with various other pattern-recognition technologies. He is well-versed in what technology is theoretically capable of, and has spent his professional life trying to make it do these things.

I have nothing but good things to say about Ray Kurzweil, and this book in particular. The ideas that he puts forward may seem very optimistic, sometimes verging on techno-fanaticism, but nothing he is saying is negative. If he's right, the human race only has to survive until the 2040s and things will markedly improve.

However excellent I found the technological predictions made in this book, there are two points that brought it down to four stars. First, and a matter I admit is one of personal preference, there were far too many graphs to do with economy and business. This is an American book, so capitalism has to figure somewhere, and he is forgiven. The other point is that some of the speculations he is making are sociological ones and these are far more spurious than any technological speculations. However, they are not fundamental to what he is arguing.

All in all, an excellent, if at times overwhelming, read. I heartily recommend it as an introduction to transhumanism and futurism.

Revelatory, 21 Mar 2008
I discovered this book a couple of years ago. There was a sale at Waterstone's, and I had all but one of the books needed to take advantage of said sale. This took my interest, so I got a hold of it, and thank goodness I did.

I can honestly say that this is the most important non-fiction book I have ever read, and quite possibly one of the most important books period. Whilst I have always sensed something important might be taking place regarding technology, and I have always had a deep love of science and technology, Kurzweil highlights and articulates some incredible and illustrative concepts. I don't agree with everything he says, but the fundaments of the book seem entirely solid. Sometimes this terrifies me, but Kurzweil offers a great deal of hope as well.

Whether you embrace or reject the implications, however, Kurzweil's book makes an extremely imposing case that I have yet to see refuted. Reading it will prepare you for the future, whether that future looks glorious or horrifying to you.

Awesome book, 24 Jan 2008
My heart sank when I got this book. An American book on science that had that many pages must be written by someone who got paid by how many times they were able to repeat themselves. This has been my experience with books much thinner than this. Yet I was quite wrong. There is very little repetition and it is all appropriate. The book is very well written with careful attention given to the order in which ideas are presented. It is an astonishingly wide ranging book and essential reading for anyone who is interested in where technology is taking us. How the author found time to write it, along with perfoming all his other duties beats me. He must be one hell of a guy!
The only thing I take issue with him on, is... no I won't spoil it for you! You can make up your own mind. Just read it!

good reference reference book but..., 11 Jul 2007
..don't like the writing style. Fewer equations and more explanations would have made it a better book.



Great insights, but a hard read, 14 Jun 2007
This new book by Chris Bishop covers most areas of pattern recognition quite exhaustively. The author is an expert, this is evidenced by the excellent insights he gives into the complex math behind the machine learning algorithms. I have worked for quite some time with neural networks and have had coursework in linear algebra, probability and regression analysis, and hence found some of the stuff in the book quite illuminating.

But that said, I must point out that the book is very math heavy. Inspite of my considerable background in the area of neural networks, I still was struggling with the equations. This is certainly not the book that can teach one things from the ground up, and thats why I would give it only 3 stars. I am new to kernels, and I am finding the relevant chapters quite confusing. For those who want to build powerful machine learning solutions to their problems, I am sorry but they will have to look elsewhere. This book cant help you build an application, another serious drawback in my opinion. The intended audience for this book I guess are PhD students/researchers who are working with the math related aspects of machine learning, and not undergraduates or working professionals who want to write machine learning code for their applications/projects.

Best book of its kind I have found, 24 Mar 2007
Bishop does an excellent job of helping the reader visualize what is going on in the problems and techniques he describes, emphasizing an intuitive grasp of the issues without sacrificing mathematical rigour. The writing is clear and the production is excellent. Strongly recommended both for anyone serious about getting into machine learning and for those already working in it.


Excellent book, 29 Jan 2007
As a newbie to pattern recognition I found this book very helpful. It is the clearest book I ever read! Accompanying examples and material are very illuminating. I particularly appreciated the gradual introduction of key concepts, often accompanied with practical examples and stimulating exercises.

Great tour of physics, not sure about the metaphysics, 15 Aug 2008
I give this book five stars cos it occupies, along with Barrow and Tipler's The Anthropic Cosmological Principle (Oxford Paperbacks) a niche that nothing else quite does. It is on the furthest edge of popular science writing before you penetrate into the realm of the specialist. So for a person like me with undergraduate maths it gave me a lot of information without intolerable effort. It was tough going but very worthwhile. For anyone with less than A-level (I mean 70's A-level) maths though, I'd stick with the books with no equations, like the very popular A Brief History of Time: From the Big Bang to Black Holes, which I rate more as a human interest story than as an introduction to any actual cosmology.

As for Penrose's conjectures about the mental. Well, his ideas have been around for a while now and as far as I can tell have not led us to anything new. He exhibits the common fuzziness of the day, that is only really now getting tightened up on in the Philosophy of Mind literature, of conflating the problem of mentation, i.e. what goes on in the mind of a mathematician when she's having a great insight, with the problem of consciousness, i.e. what is it? They are both profound and mysterious problems but they are not the same problem, and not even necessarily related. I can still see a space for how quantum mechanical, i.e. truly random, processes might get exploited in pruning decision trees when searching a problem space, i.e. with respect the mentation problem. But how quantum randomness might contribute to consciousness seems more problematic.

The most incisive contribution to the question of consciousness I'm aware of right now is Edelman & Tononi's A Universe of Consciousness How Matter Becomes Imagination.

But this book is great for the physics, and certainly at the limits of what someone of my educational background can indulge in as a spare time activity. Penrose's next book on this topic Shadows of the Mind: A Search for the Missing Science of Consciousness was more mathematically rigorous and lost me pretty well straight away.

Skip this, 11 Aug 2008
The one redeeming feature this book had was its overview of theoretical physics. The chapters bookending the good bit were a complete nonsense. Penrose has now produced another, more in-depth and quite superb, version of his take on physics in The Road to Reality, thereby obviating the need for this title.

Stylistic difficulties mask an outstanding book, 30 Dec 2007
Penrose does not shrink from the difficult when trying to explain the problems he's obsessed about. This is one of the best books on the subject (the subject in question being "What's it all about, really, when you come to think of it?"), and I can't think of anyone else who's treading the same ground in the same way (Hawking's rather more specialised and abstruse, Greene centres mainly on the details of the physics and Hofstadter's more into the logic and philosophy).

However, I have difficulty with Penrose's style, and find he can be a bit difficult to follow sometimes. Having said that, it's no easy task to put all these concepts into plain prose. I know I couldn't do it.

Entertaining and Mathematically Advanced, 21 Jul 2006
I found this book stimulating and entertaining in equal measure. It looks at the questions such as -- if we had enough information, we could predict absolutely everything, or not? Is the human mind simply a machine (for example a computer)? Can we actually be transported Star-trek style or not? Are we (including our memories) just a collection of atoms that could be reconstituted?

In answering these questions Penrose embarks on a tour of the mathematical concepts and theories that underpin our understanding of the Universe.

There seems to be much more maths than is really needed, and there is a lot of theory (The book runs to over 500 pages after all). You will also need advanced A level maths to cope (on the basis that I just coped, and that's the level of maths I reached).

Entertaining and enjoyable IF you are interested in Maths. If you are not, stay away.

Misleading Title, 13 May 2003
The book digreses too far from its title with long detailed coverage of mathematical proofs and descriptions of quantum mechanics. The material could be bypassed or expressed more succingtly. The final conclusion is rather weak: somehow thanks to the hard or impossible to predict nature of sub-atomic events: free-will and human nature will still survive beyond the reach of computing.

Revised and ready to lead you down a good path, 21 May 2006
Having read the first edition, the authors earn the extra rating because they've managed to improve on their work and practical WEKA resource offering. Without a doubt, an essential read for people who are both new and experienced in the fields of data mining, descriptive & predictive analytics or state & behavioural modelling.

The volume of material on the market today is still quite limited and in the gap between the first and second edition of this book, quite a lot has actually changed in the field. In my view, book content has only marginally progressed with the times, perhaps in favour of attempting to attract and activate new members, practictioners and commercially oriented researchers to the fore of data mining. It's a bold step to evolve material as the field evolves; those breaking new ground in this area should be more visible and offered greater support.

I believe that there is room in the market now for some revised materials covering anomalised commercial implementations of Advanced Data Mining & AI Concepts. A small community of authors could plug this gap really well.

A good book, does the job, 03 Sep 2008
A good book for game AI to get you started, the text reads fine and is easy to follow. The code on the other hand is rather messy, and I agree with the other reviewer that pseudo code would have been a better option - you have to read through all the authors little coding habits to root out what you need.

Still, worth a read because the AI descriptions are very well put together.



Nicely done., 08 Mar 2007
First off, it's a good read as it is so well written. There is an invaluable basic maths/physics primer at the
start (in fact I still refer to that section a year later). Then a nice gentle intro with FSMs (although, on my girlfriends orders, I had to rewrite the tasks given to the Miner's Wife). From there it's Steering Behaviours, Sports AI, Pathfinding etc (all the usual suspects) but the examples for each are superb. I did struggle slightly translating the code
(pseudo-code would have been nice) but that's a minor point.


A great book, with some significant gaps., 17 Jan 2005
This is a great book for hobbiest game developers, and professionals new to AI. It gives a good overview of some of the most interested areas of game AI, and practical solutions to make progress.

It is the first book I've seen that makes a good effort to present solutions that would actually be used in real games. Which surprised me, because Mat's first book on game AI was just like every other title I've read: a blend of hype and unusable technology. With this book he has come on by miles.

I'm AI programmer in the industry, and this is the first book I've seen that I could hand-on-heart recommend for real technology (John Funge's book is also good, but as an overview, not for practical implementation).

There are some bits (such as the scripting chapter) that are squarely aimed outside the industry, but provide superb material for a hobbiest. The majority of the book is filled with technology that covers the very basics of game AI for novice AI developers. And there are some bits (like the goal oriented behaviour chapter) that could actually benefit people working on commercial games.

There are bits I disagreed with, inevitably.

My biggest criticism of the book is its narrow scope. It covers a handful of AI techniques well, but doesn't talk about the tens of other techniques that game AI programmers need to use to get the game out of the door. It also misses lots of techniques used in particular game genres (it is focussed primarily on shooters, although there is a chapter with some small inspiration for sports games). Some of this is because of size, but it means that the book can only act as a taster and not a real reference book.

Mat's writing is chirpy and readable, and so far the code is reasonably correct and useful. I would recommend it if you are a hobbiest game developer, but its probably far beneath you if you already work in AI in the industry.

A must have., 11 Nov 2004
The book uses source code (C++) and UML diagrams to explain AI techniques that can be found in various games in a simple yet precise manner. Each chapter has a practical Visual C++ project, which can be used as a framework to expand on the ideas presented. I thoroughly recommend this book, not only for AI programmers, but programmers in general, as it re-inforces good software engineering practices in an industry that largely discards them.

Overall, an excellent book. This is how AI should be taught at University.

Excellent. Thought-provoking., 18 May 2008
A very well presented, and extremely well researched effort. Everyone should read this. One star deducted jointly for the shameless (and frequent) promotion of the author's other works, and the sometimes unnecessarily long-winded passages in the book - its still very well done, but this is my own opinion.

I strongly recommend this book, very hard to put down.

Contains some wonderful ideas., 30 Apr 2008
For those of you who don't know, Ray Kurzweil is the man who invented Optical Character Recognition, along with various other pattern-recognition technologies. He is well-versed in what technology is theoretically capable of, and has spent his professional life trying to make it do these things.

I have nothing but good things to say about Ray Kurzweil, and this book in particular. The ideas that he puts forward may seem very optimistic, sometimes verging on techno-fanaticism, but nothing he is saying is negative. If he's right, the human race only has to survive until the 2040s and things will markedly improve.

However excellent I found the technological predictions made in this book, there are two points that brought it down to four stars. First, and a matter I admit is one of personal preference, there were far too many graphs to do with economy and business. This is an American book, so capitalism has to figure somewhere, and he is forgiven. The other point is that some of the speculations he is making are sociological ones and these are far more spurious than any technological speculations. However, they are not fundamental to what he is arguing.

All in all, an excellent, if at times overwhelming, read. I heartily recommend it as an introduction to transhumanism and futurism.

Revelatory, 21 Mar 2008
I discovered this book a couple of years ago. There was a sale at Waterstone's, and I had all but one of the books needed to take advantage of said sale. This took my interest, so I got a hold of it, and thank goodness I did.

I can honestly say that this is the most important non-fiction book I have ever read, and quite possibly one of the most important books period. Whilst I have always sensed something important might be taking place regarding technology, and I have always had a deep love of science and technology, Kurzweil highlights and articulates some incredible and illustrative concepts. I don't agree with everything he says, but the fundaments of the book seem entirely solid. Sometimes this terrifies me, but Kurzweil offers a great deal of hope as well.

Whether you embrace or reject the implications, however, Kurzweil's book makes an extremely imposing case that I have yet to see refuted. Reading it will prepare you for the future, whether that future looks glorious or horrifying to you.

Awesome book, 24 Jan 2008
My heart sank when I got this book. An American book on science that had that many pages must be written by someone who got paid by how many times they were able to repeat themselves. This has been my experience with books much thinner than this. Yet I was quite wrong. There is very little repetition and it is all appropriate. The book is very well written with careful attention given to the order in which ideas are presented. It is an astonishingly wide ranging book and essential reading for anyone who is interested in where technology is taking us. How the author found time to write it, along with perfoming all his other duties beats me. He must be one hell of a guy!
The only thing I take issue with him on, is... no I won't spoil it for you! You can make up your own mind. Just read it!

good reference reference book but..., 11 Jul 2007
..don't like the writing style. Fewer equations and more explanations would have made it a better book.



Great insights, but a hard read, 14 Jun 2007
This new book by Chris Bishop covers most areas of pattern recognition quite exhaustively. The author is an expert, this is evidenced by the excellent insights he gives into the complex math behind the machine learning algorithms. I have worked for quite some time with neural networks and have had coursework in linear algebra, probability and regression analysis, and hence found some of the stuff in the book quite illuminating.

But that said, I must point out that the book is very math heavy. Inspite of my considerable background in the area of neural networks, I still was struggling with the equations. This is certainly not the book that can teach one things from the ground up, and thats why I would give it only 3 stars. I am new to kernels, and I am finding the relevant chapters quite confusing. For those who want to build powerful machine learning solutions to their problems, I am sorry but they will have to look elsewhere. This book cant help you build an application, another serious drawback in my opinion. The intended audience for this book I guess are PhD students/researchers who are working with the math related aspects of machine learning, and not undergraduates or working professionals who want to write machine learning code for their applications/projects.

Best book of its kind I have found, 24 Mar 2007
Bishop does an excellent job of helping the reader visualize what is going on in the problems and techniques he describes, emphasizing an intuitive grasp of the issues without sacrificing mathematical rigour. The writing is clear and the production is excellent. Strongly recommended both for anyone serious about getting into machine learning and for those already working in it.


Excellent book, 29 Jan 2007
As a newbie to pattern recognition I found this book very helpful. It is the clearest book I ever read! Accompanying examples and material are very illuminating. I particularly appreciated the gradual introduction of key concepts, often accompanied with practical examples and stimulating exercises.

Great tour of physics, not sure about the metaphysics, 15 Aug 2008
I give this book five stars cos it occupies, along with Barrow and Tipler's The Anthropic Cosmological Principle (Oxford Paperbacks) a niche that nothing else quite does. It is on the furthest edge of popular science writing before you penetrate into the realm of the specialist. So for a person like me with undergraduate maths it gave me a lot of information without intolerable effort. It was tough going but very worthwhile. For anyone with less than A-level (I mean 70's A-level) maths though, I'd stick with the books with no equations, like the very popular A Brief History of Time: From the Big Bang to Black Holes, which I rate more as a human interest story than as an introduction to any actual cosmology.

As for Penrose's conjectures about the mental. Well, his ideas have been around for a while now and as far as I can tell have not led us to anything new. He exhibits the common fuzziness of the day, that is only really now getting tightened up on in the Philosophy of Mind literature, of conflating the problem of mentation, i.e. what goes on in the mind of a mathematician when she's having a great insight, with the problem of consciousness, i.e. what is it? They are both profound and mysterious problems but they are not the same problem, and not even necessarily related. I can still see a space for how quantum mechanical, i.e. truly random, processes might get exploited in pruning decision trees when searching a problem space, i.e. with respect the mentation problem. But how quantum randomness might contribute to consciousness seems more problematic.

The most incisive contribution to the question of consciousness I'm aware of right now is Edelman & Tononi's A Universe of Consciousness How Matter Becomes Imagination.

But this book is great for the physics, and certainly at the limits of what someone of my educational background can indulge in as a spare time activity. Penrose's next book on this topic Shadows of the Mind: A Search for the Missing Science of Consciousness was more mathematically rigorous and lost me pretty well straight away.

Skip this, 11 Aug 2008
The one redeeming feature this book had was its overview of theoretical physics. The chapters bookending the good bit were a complete nonsense. Penrose has now produced another, more in-depth and quite superb, version of his take on physics in The Road to Reality, thereby obviating the need for this title.

Stylistic difficulties mask an outstanding book, 30 Dec 2007
Penrose does not shrink from the difficult when trying to explain the problems he's obsessed about. This is one of the best books on the subject (the subject in question being "What's it all about, really, when you come to think of it?"), and I can't think of anyone else who's treading the same ground in the same way (Hawking's rather more specialised and abstruse, Greene centres mainly on the details of the physics and Hofstadter's more into the logic and philosophy).

However, I have difficulty with Penrose's style, and find he can be a bit difficult to follow sometimes. Having said that, it's no easy task to put all these concepts into plain prose. I know I couldn't do it.

Entertaining and Mathematically Advanced, 21 Jul 2006
I found this book stimulating and entertaining in equal measure. It looks at the questions such as -- if we had enough information, we could predict absolutely everything, or not? Is the human mind simply a machine (for example a computer)? Can we actually be transported Star-trek style or not? Are we (including our memories) just a collection of atoms that could be reconstituted?

In answering these questions Penrose embarks on a tour of the mathematical concepts and theories that underpin our understanding of the Universe.

There seems to be much more maths than is really needed, and there is a lot of theory (The book runs to over 500 pages after all). You will also need advanced A level maths to cope (on the basis that I just coped, and that's the level of maths I reached).

Entertaining and enjoyable IF you are interested in Maths. If you are not, stay away.

Misleading Title, 13 May 2003
The book digreses too far from its title with long detailed coverage of mathematical proofs and descriptions of quantum mechanics. The material could be bypassed or expressed more succingtly. The final conclusion is rather weak: somehow thanks to the hard or impossible to predict nature of sub-atomic events: free-will and human nature will still survive beyond the reach of computing.

Revised and ready to lead you down a good path, 21 May 2006
Having read the first edition, the authors earn the extra rating because they've managed to improve on their work and practical WEKA resource offering. Without a doubt, an essential read for people who are both new and experienced in the fields of data mining, descriptive & predictive analytics or state & behavioural modelling.

The volume of material on the market today is still quite limited and in the gap between the first and second edition of this book, quite a lot has actually changed in the field. In my view, book content has only marginally progressed with the times, perhaps in favour of attempting to attract and activate new members, practictioners and commercially oriented researchers to the fore of data mining. It's a bold step to evolve material as the field evolves; those breaking new ground in this area should be more visible and offered greater support.

I believe that there is room in the market now for some revised materials covering anomalised commercial implementations of Advanced Data Mining & AI Concepts. A small community of authors could plug this gap really well.

A good book, does the job, 03 Sep 2008
A good book for game AI to get you started, the text reads fine and is easy to follow. The code on the other hand is rather messy, and I agree with the other reviewer that pseudo code would have been a better option - you have to read through all the authors little coding habits to root out what you need.

Still, worth a read because the AI descriptions are very well put together.



Nicely done., 08 Mar 2007
First off, it's a good read as it is so well written. There is an invaluable basic maths/physics primer at the
start (in fact I still refer to that section a year later). Then a nice gentle intro with FSMs (although, on my girlfriends orders, I had to rewrite the tasks given to the Miner's Wife). From there it's Steering Behaviours, Sports AI, Pathfinding etc (all the usual suspects) but the examples for each are superb. I did struggle slightly translating the code
(pseudo-code would have been nice) but that's a minor point.


A great book, with some significant gaps., 17 Jan 2005
This is a great book for hobbiest game developers, and professionals new to AI. It gives a good overview of some of the most interested areas of game AI, and practical solutions to make progress.

It is the first book I've seen that makes a good effort to present solutions that would actually be used in real games. Which surprised me, because Mat's first book on game AI was just like every other title I've read: a blend of hype and unusable technology. With this book he has come on by miles.

I'm AI programmer in the industry, and this is the first book I've seen that I could hand-on-heart recommend for real technology (John Funge's book is also good, but as an overview, not for practical implementation).

There are some bits (such as the scripting chapter) that are squarely aimed outside the industry, but provide superb material for a hobbiest. The majority of the book is filled with technology that covers the very basics of game AI for novice AI developers. And there are some bits (like the goal oriented behaviour chapter) that could actually benefit people working on commercial games.

There are bits I disagreed with, inevitably.

My biggest criticism of the book is its narrow scope. It covers a handful of AI techniques well, but doesn't talk about the tens of other techniques that game AI programmers need to use to get the game out of the door. It also misses lots of techniques used in particular game genres (it is focussed primarily on shooters, although there is a chapter with some small inspiration for sports games). Some of this is because of size, but it means that the book can only act as a taster and not a real reference book.

Mat's writing is chirpy and readable, and so far the code is reasonably correct and useful. I would recommend it if you are a hobbiest game developer, but its probably far beneath you if you already work in AI in the industry.

A must have., 11 Nov 2004
The book uses source code (C++) and UML diagrams to explain AI techniques that can be found in various games in a simple yet precise manner. Each chapter has a practical Visual C++ project, which can be used as a framework to expand on the ideas presented. I thoroughly recommend this book, not only for AI programmers, but programmers in general, as it re-inforces good software engineering practices in an industry that largely discards them.

Overall, an excellent book. This is how AI should be taught at University.

Complete Coverage of the topic, 21 May 2001
Covers Machine Learning concepts thoroughly, allowing you to decide which type is best for any particular problem. Uses some daunting mathematical notation, but still easy to follow

Excellent overview of all major machine learning topics., 16 Jul 1999
I first used this book as the required text for my course in ML in 1997 and got rave reviews from the students. I will be using it again in 1999. I found ALL of the major topics and issues in ML addressed. The book is easily readable with anyone with a computer science background, and the book works quite well in a wide variety of approaches to presentation at the advanced undergraduate and graduate levels.

This book has proselytized me!!!!, 10 May 1999
Everything I will do in the future will be based on ML and just one semester of an ML course & this book has converted me(even though my major is not Comp.Science). Of-course this is due majorly to Dr. Thomas Ioerger and his teaching abilities(Texas A&M), but the book presents all concepts(even seemingly complex ones) in a way that is easy and enjoyable to learn. One of the most useful books I've ever studied!

Excellent. Thought-provoking., 18 May 2008
A very well presented, and extremely well researched effort. Everyone should read this. One star deducted jointly for the shameless (and frequent) promotion of the author's other works, and the sometimes unnecessarily long-winded passages in the book - its still very well done, but this is my own opinion.

I strongly recommend this book, very hard to put down.

Contains some wonderful ideas., 30 Apr 2008
For those of you who don't know, Ray Kurzweil is the man who invented Optical Character Recognition, along with various other pattern-recognition technologies. He is well-versed in what technology is theoretically capable of, and has spent his professional life trying to make it do these things.

I have nothing but good things to say about Ray Kurzweil, and this book in particular. The ideas that he puts forward may seem very optimistic, sometimes verging on techno-fanaticism, but nothing he is saying is negative. If he's right, the human race only has to survive until the 2040s and things will markedly improve.

However excellent I found the technological predictions made in this book, there are two points that brought it down to four stars. First, and a matter I admit is one of personal preference, there were far too many graphs to do with economy and business. This is an American book, so capitalism has to figure somewhere, and he is forgiven. The other point is that some of the speculations he is making are sociological ones and these are far more spurious than any technological speculations. However, they are not fundamental to what he is arguing.

All in all, an excellent, if at times overwhelming, read. I heartily recommend it as an introduction to transhumanism and futurism.

Revelatory, 21 Mar 2008
I discovered this book a couple of years ago. There was a sale at Waterstone's, and I had all but one of the books needed to take advantage of said sale. This took my interest, so I got a hold of it, and thank goodness I did.

I can honestly say that this is the most important non-fiction book I have ever read, and quite possibly one of the most important books period. Whilst I have always sensed something important might be taking place regarding technology, and I have always had a deep love of science and technology, Kurzweil highlights and articulates some incredible and illustrative concepts. I don't agree with everything he says, but the fundaments of the book seem entirely solid. Sometimes this terrifies me, but Kurzweil offers a great deal of hope as well.

Whether you embrace or reject the implications, however, Kurzweil's book makes an extremely imposing case that I have yet to see refuted. Reading it will prepare you for the future, whether that future looks glorious or horrifying to you.

Awesome book, 24 Jan 2008
My heart sank when I got this book. An American book on science that had that many pages must be written by someone who got paid by how many times they were able to repeat themselves. This has been my experience with books much thinner than this. Yet I was quite wrong. There is very little repetition and it is all appropriate. The book is very well written with careful attention given to the order in which ideas are presented. It is an astonishingly wide ranging book and essential reading for anyone who is interested in where technology is taking us. How the author found time to write it, along with perfoming all his other duties beats me. He must be one hell of a guy!
The only thing I take issue with him on, is... no I won't spoil it for you! You can make up your own mind. Just read it!

good reference reference book but..., 11 Jul 2007
..don't like the writing style. Fewer equations and more explanations would have made it a better book.



Great insights, but a hard read, 14 Jun 2007
This new book by Chris Bishop covers most areas of pattern recognition quite exhaustively. The author is an expert, this is evidenced by the excellent insights he gives into the complex math behind the machine learning algorithms. I have worked for quite some time with neural networks and have had coursework in linear algebra, probability and regression analysis, and hence found some of the stuff in the book quite illuminating.

But that said, I must point out that the book is very math heavy. Inspite of my considerable background in the area of neural networks, I still was struggling with the equations. This is certainly not the book that can teach one things from the ground up, and thats why I would give it only 3 stars. I am new to kernels, and I am finding the relevant chapters quite confusing. For those who want to build powerful machine learning solutions to their problems, I am sorry but they will have to look elsewhere. This book cant help you build an application, another serious drawback in my opinion. The intended audience for this book I guess are PhD students/researchers who are working with the math related aspects of machine learning, and not undergraduates or working professionals who want to write machine learning code for their applications/projects.

Best book of its kind I have found, 24 Mar 2007
Bishop does an excellent job of helping the reader visualize what is going on in the problems and techniques he describes, emphasizing an intuitive grasp of the issues without sacrificing mathematical rigour. The writing is clear and the production is excellent. Strongly recommended both for anyone serious about getting into machine learning and for those already working in it.


Excellent book, 29 Jan 2007
As a newbie to pattern recognition I found this book very helpful. It is the clearest book I ever read! Accompanying examples and material are very illuminating. I particularly appreciated the gradual introduction of key concepts, often accompanied with practical examples and stimulating exercises.

Great tour of physics, not sure about the metaphysics, 15 Aug 2008
I give this book five stars cos it occupies, along with Barrow and Tipler's The Anthropic Cosmological Principle (Oxford Paperbacks) a niche that nothing else quite does. It is on the furthest edge of popular science writing before you penetrate into the realm of the specialist. So for a person like me with undergraduate maths it gave me a lot of information without intolerable effort. It was tough going but very worthwhile. For anyone with less than A-level (I mean 70's A-level) maths though, I'd stick with the books with no equations, like the very popular A Brief History of Time: From the Big Bang to Black Holes, which I rate more as a human interest story than as an introduction to any actual cosmology.

As for Penrose's conjectures about the mental. Well, his ideas have been around for a while now and as far as I can tell have not led us to anything new. He exhibits the common fuzziness of the day, that is only really now getting tightened up on in the Philosophy of Mind literature, of conflating the problem of mentation, i.e. what goes on in the mind of a mathematician when she's having a great insight, with the problem of consciousness, i.e. what is it? They are both profound and mysterious problems but they are not the same problem, and not even necessarily related. I can still see a space for how quantum mechanical, i.e. truly random, processes might get exploited in pruning decision trees when searching a problem space, i.e. with respect the mentation problem. But how quantum randomness might contribute to consciousness seems more problematic.

The most incisive contribution to the question of consciousness I'm aware of right now is Edelman & Tononi's A Universe of Consciousness How Matter Becomes Imagination.

But this book is great for the physics, and certainly at the limits of what someone of my educational background can indulge in as a spare time activity. Penrose's next book on this topic Shadows of the Mind: A Search for the Missing Science of Consciousness was more mathematically rigorous and lost me pretty well straight away.

Skip this, 11 Aug 2008
The one redeeming feature this book had was its overview of theoretical physics. The chapters bookending the good bit were a complete nonsense. Penrose has now produced another, more in-depth and quite superb, version of his take on physics in The Road to Reality, thereby obviating the need for this title.

Stylistic difficulties mask an outstanding book, 30 Dec 2007
Penrose does not shrink from the difficult when trying to explain the problems he's obsessed about. This is one of the best books on the subject (the subject in question being "What's it all about, really, when you come to think of it?"), and I can't think of anyone else who's treading the same ground in the same way (Hawking's rather more specialised and abstruse, Greene centres mainly on the details of the physics and Hofstadter's more into the logic and philosophy).

However, I have difficulty with Penrose's style, and find he can be a bit difficult to follow sometimes. Having said that, it's no easy task to put all these concepts into plain prose. I know I couldn't do it.

Entertaining and Mathematically Advanced, 21 Jul 2006
I found this book stimulating and entertaining in equal measure. It looks at the questions such as -- if we had enough information, we could predict absolutely everything, or not? Is the human mind simply a machine (for example a computer)? Can we actually be transported Star-trek style or not? Are we (including our memories) just a collection of atoms that could be reconstituted?

In answering these questions Penrose embarks on a tour of the mathematical concepts and theories that underpin our understanding of the Universe.

There seems to be much more maths than is really needed, and there is a lot of theory (The book runs to over 500 pages after all). You will also need advanced A level maths to cope (on the basis that I just coped, and that's the level of maths I reached).

Entertaining and enjoyable IF you are interested in Maths. If you are not, stay away.

Misleading Title, 13 May 2003
The book digreses too far from its title with long detailed coverage of mathematical proofs and descriptions of quantum mechanics. The material could be bypassed or expressed more succingtly. The final conclusion is rather weak: somehow thanks to the hard or impossible to predict nature of sub-atomic events: free-will and human nature will still survive beyond the reach of computing.

Revised and ready to lead you down a good path, 21 May 2006
Having read the first edition, the authors earn the extra rating because they've managed to improve on their work and practical WEKA resource offering. Without a doubt, an essential read for people who are both new and experienced in the fields of data mining, descriptive & predictive analytics or state & behavioural modelling.

The volume of material on the market today is still quite limited and in the gap between the first and second edition of this book, quite a lot has actually changed in the field. In my view, book content has only marginally progressed with the times, perhaps in favour of attempting to attract and activate new members, practictioners and commercially oriented researchers to the fore of data mining. It's a bold step to evolve material as the field evolves; those breaking new ground in this area should be more visible and offered greater support.

I believe that there is room in the market now for some revised materials covering anomalised commercial implementations of Advanced Data Mining & AI Concepts. A small community of authors could plug this gap really well.

A good book, does the job, 03 Sep 2008
A good book for game AI to get you started, the text reads fine and is easy to follow. The code on the other hand is rather messy, and I agree with the other reviewer that pseudo code would have been a better option - you have to read through all the authors little coding habits to root out what you need.

Still, worth a read because the AI descriptions are very well put together.



Nicely done., 08 Mar 2007
First off, it's a good read as it is so well written. There is an invaluable basic maths/physics primer at the
start (in fact I still refer to that section a year later). Then a nice gentle intro with FSMs (although, on my girlfriends orders, I had to rewrite the tasks given to the Miner's Wife). From there it's Steering Behaviours, Sports AI, Pathfinding etc (all the usual suspects) but the examples for each are superb. I did struggle slightly translating the code
(pseudo-code would have been nice) but that's a minor point.


A great book, with some significant gaps., 17 Jan 2005
This is a great book for hobbiest game developers, and professionals new to AI. It gives a good overview of some of the most interested areas of game AI, and practical solutions to make progress.

It is the first book I've seen that makes a good effort to present solutions that would actually be used in real games. Which surprised me, because Mat's first book on game AI was just like every other title I've read: a blend of hype and unusable technology. With this book he has come on by miles.

I'm AI programmer in the industry, and this is the first book I've seen that I could hand-on-heart recommend for real technology (John Funge's book is also good, but as an overview, not for practical implementation).

There are some bits (such as the scripting chapter) that are squarely aimed outside the industry, but provide superb material for a hobbiest. The majority of the book is filled with technology that covers the very basics of game AI for novice AI developers. And there are some bits (like the goal oriented behaviour chapter) that could actually benefit people working on commercial games.

There are bits I disagreed with, inevitably.

My biggest criticism of the book is its narrow scope. It covers a handful of AI techniques well, but doesn't talk about the tens of other techniques that game AI programmers need to use to get the game out of the door. It also misses lots of techniques used in particular game genres (it is focussed primarily on shooters, although there is a chapter with some small inspiration for sports games). Some of this is because of size, but it means that the book can only act as a taster and not a real reference book.

Mat's writing is chirpy and readable, and so far the code is reasonably correct and useful. I would recommend it if you are a hobbiest game developer, but its probably far beneath you if you already work in AI in the industry.

A must have., 11 Nov 2004
The book uses source code (C++) and UML diagrams to explain AI techniques that can be found in various games in a simple yet precise manner. Each chapter has a practical Visual C++ project, which can be used as a framework to expand on the ideas presented. I thoroughly recommend this book, not only for AI programmers, but programmers in general, as it re-inforces good software engineering practices in an industry that largely discards them.

Overall, an excellent book. This is how AI should be taught at University.

Complete Coverage of the topic, 21 May 2001
Covers Machine Learning concepts thoroughly, allowing you to decide which type is best for any particular problem. Uses some daunting mathematical notation, but still easy to follow

Excellent overview of all major machine learning topics., 16 Jul 1999
I first used this book as the required text for my course in ML in 1997 and got rave reviews from the students. I will be using it again in 1999. I found ALL of the major topics and issues in ML addressed. The book is easily readable with anyone with a computer science background, and the book works quite well in a wide variety of approaches to presentation at the advanced undergraduate and graduate levels.

This book has proselytized me!!!!, 10 May 1999
Everything I will do in the future will be based on ML and just one semester of an ML course & this book has converted me(even though my major is not Comp.Science). Of-course this is due majorly to Dr. Thomas Ioerger and his teaching abilities(Texas A&M), but the book presents all concepts(even seemingly complex ones) in a way that is easy and enjoyable to learn. One of the most useful books I've ever studied!

pretty much indispensible, 26 Sep 2008
This is an unqualified classic, to shelve with the likes of 'Structure and Interpretation of Computer Programs', 'Concrete Mathematics' and 'Mathematical Methods of Classical Mechanics'. If you are involved with, or interested in, high-end data analytics, then you _need_ this.

However 'high-end data analytics' does not even begin to do the book justice, so let me try again.

This is a magnificent compendium of fascinating stuff presented in a coherent information-theoretic framework. It covers everything from how digital television data compression and CD error correction work to a detailed commentary on neural networks, and discussion of principled AI methods such as clustering, Gaussian processes and probabilistic graphical models, together with Monte-Carlo techniques and a bunch of statistical physics. It even throws in a complete course in Bayesian statistics. It reads like a really good 'popular' 'science' book (I often wonder where the scare quotes should be) that doesn't bother to try to be popular.

In fact I bought this originally as bedside reading, for pleasure. It was only later that I actually used it for anything.


Fun packed, information packed, but uncluttered., 09 Mar 2005
Uniting information theory and inference in an interactive and entertaining way, this book has been a constant source of inspiration, intuition and insight for me. It is packed full of stuff - its contents appear to grow the more I look - but the layering of the material means the abundance of topics does not confuse.

This is _not_ just a book for the experts. However, you will need to think and interact when reading it. That is, after all, how you learn, and the book helps and guides you in this with many puzzles and problems.

Excellent book on inference and learning ..., 21 Nov 2003
I have been able to use this book as extra background material for several courses of my final undergraduate year.

First I have been able to find a lot of usefull information on coding theory. Although this book isn't meanth to be a treatise on several coding, decoding techniques it gives the reader a lot of insight in the connection between coding and information theory. You won't find how matrix decoding algorithms, cyclic codes etc work but you will find out how the limits of information theory restrict coding theory.

I cannot compare the information theoretic approach to any other book as this was my first introduction but I can say the information theoretic treatise was a good read and I make myself strong I now have a solid information theory background.

Another course for which I have been able to use this book was a course on uncertainty reasoning. Mckay's book covers inference in great depth and introduces the reader to several different area's such as belief networks, decision theory, bayesian networks and several other inference methods. As before I cannot compare the ising, monte carlo like methods but it did give me a good introduction. Concerning the bayesian probability/inference, decision theory I can only say this is THE best introduction I have read!

I have read several introductions on Neural Networks (Kevin Geurny). This book keeps up with the standard set by several other good introductions.

Inference/Learning is a vast research area and this books gives a good introduction in all areas. Even as the part on neural networks may be as good as some other books on the topic I would definitely advise this book as for the same price you get so much more introductions to other learning techniques. The last thing which I like very much is the fact that several excercies are solved or come with hints which makes it for a student a very good book accompanying other courses. The author has a very clear writing style and knows when to add a good joke to make the reading more enjoyable.

My conclusion: if you are an undergraduate student interested in learning and inference -> "Go get this book asap!!!"

Excellent. Thought-provoking., 18 May 2008
A very well presented, and extremely well researched effort. Everyone should read this. One star deducted jointly for the shameless (and frequent) promotion of the author's other works, and the sometimes unnecessarily long-winded passages in the book - its still very well done, but this is my own opinion.

I strongly recommend this book, very hard to put down.

Contains some wonderful ideas., 30 Apr 2008
For those of you who don't know, Ray Kurzweil is the man who invented Optical Character Recognition, along with various other pattern-recognition technologies. He is well-versed in what technology is theoretically capable of, and has spent his professional life trying to make it do these things.

I have nothing but good things to say about Ray Kurzweil, and this book in particular. The ideas that he puts forward may seem very optimistic, sometimes verging on techno-fanaticism, but nothing he is saying is negative. If he's right, the human race only has to survive until the 2040s and things will markedly improve.

However excellent I found the technological predictions made in this book, there are two points that brought it down to four stars. First, and a matter I admit is one of personal preference, there were far too many graphs to do with economy and business. This is an American book, so capitalism has to figure somewhere, and he is forgiven. The other point is that some of the speculations he is making are sociological ones and these are far more spurious than any technological speculations. However, they are not fundamental to what he is arguing.

All in all, an excellent, if at times overwhelming, read. I heartily recommend it as an introduction to transhumanism and futurism.

Revelatory, 21 Mar 2008
I discovered this book a couple of years ago. There was a sale at Waterstone's, and I had all but one of the books needed to take advantage of said sale. This took my interest, so I got a hold of it, and thank goodness I did.

I can honestly say that this is the most important non-fiction book I have ever read, and quite possibly one of the most important books period. Whilst I have always sensed something important might be taking place regarding technology, and I have always had a deep love of science and technology, Kurzweil highlights and articulates some incredible and illustrative concepts. I don't agree with everything he says, but the fundaments of the book seem entirely solid. Sometimes this terrifies me, but Kurzweil offers a great deal of hope as well.

Whether you embrace or reject the implications, however, Kurzweil's book makes an extremely imposing case that I have yet to see refuted. Reading it will prepare you for the future, whether that future looks glorious or horrifying to you.

Awesome book, 24 Jan 2008
My heart sank when I got this book. An American book on science that had that many pages must be written by someone who got paid by how many times they were able to repeat themselves. This has been my experience with books much thinner than this. Yet I was quite wrong. There is very little repetition and it is all appropriate. The book is very well written with careful attention given to the order in which ideas are presented. It is an astonishingly wide ranging book and essential reading for anyone who is interested in where technology is taking us. How the author found time to write it, along with perfoming all his other duties beats me. He must be one hell of a guy!
The only thing I take issue with him on, is... no I won't spoil it for you! You can make up your own mind. Just read it!

good reference reference book but..., 11 Jul 2007
..don't like the writing style. Fewer equations and more explanations would have made it a better book.



Great insights, but a hard read, 14 Jun 2007
This new book by Chris Bishop covers most areas of pattern recognition quite exhaustively. The author is an expert, this is evidenced by the excellent insights he gives into the complex math behind the machine learning algorithms. I have worked for quite some time with neural networks and have had coursework in linear algebra, probability and regression analysis, and hence found some of the stuff in the book quite illuminating.

But that said, I must point out that the book is very math heavy. Inspite of my considerable background in the area of neural networks, I still was struggling with the equations. This is certainly not the book that can teach one things from the ground up, and thats why I would give it only 3 stars. I am new to kernels, and I am finding the relevant chapters quite confusing. For those who want to build powerful machine learning solutions to their problems, I am sorry but they will have to look elsewhere. This book cant help you build an application, another serious drawback in my opinion. The intended audience for this book I guess are PhD students/researchers who are working with the math related aspects of machine learning, and not undergraduates or working professionals who want to write machine learning code for their applications/projects.

Best book of its kind I have found, 24 Mar 2007
Bishop does an excellent job of helping the reader visualize what is going on in the problems and techniques he describes, emphasizing an intuitive grasp of the issues without sacrificing mathematical rigour. The writing is clear and the production is excellent. Strongly recommended both for anyone serious about getting into machine learning and for those already working in it.


Excellen