This book is excellent! And intriguing.

The writers main goal is to explain how human brain works. And he does that well! Every word in this book makes sense. Based on huge amount of examples he surprises with the elegant outcome.
The writer also claims that the computer science in general is lost on its track towards artificial intelligence. Computers with the architecture today cannot reach much higher goals of intelligence. As IT-developper, I totally agree: until we continue building Turing machines, the information systems are stuck with tremendous amount of information with no proper use (think about Internet).
So, while making intriguing, even revolutionary assertions, writer maintains pragmatic and humorous writing style and good contact with reader. And he succeeds to make himself totally clear.

It is good reading even though you may not be into science; who wouldn't be interested to know what human thinking is about!

Back in 1977 Carl Sagan's Pulitzer Prize winning Dragons of Eden introduced us to Reptilian brain and the revolutionary idea that most of our brain is much older than humankind. Hawkins takes this fascinating subject to the next level by asking what it is that the neocortex, that part of the brain that only mammals possess, does. Just like Sagan, his speculations give us a new way of looking at ourselves and what it means to be an intelligent being.

He comes to the subject with a unique background that combines inside knowledge of how computers work with a lifelong passion for understanding the brain. This enables him to explain his ideas in a way that is approachable to all readers.

His explanations of how artificial intelligence and neural networks fail to consider what brains "really do" is very valuable. Finally he makes a convincing argument that intelligence should be measured, not by behaviour, but by the ability to make predictions.

His "theory" may not pan out in all its details but he makes an important contribution by looking at the subject from a productive point of view. Also, the book is a wonderful introduction to how the neocortex functions. It is true that he does not go into the philosophical implications of his ideas, but he admits outright that he is not a philosopher.

I love the passion Jeff brings to this subject. I don't know if he is right, at least on the right track, or simply wrong, but this book makes you think about thinking, and that is a good thing.

I have studied many learning theories and I think Jeff's theory of intelligence (learning) answers more questions than most of the other theories, and deserves to be more fully explored. I am specifically interested in how e-learning could be built based on his theory. I hope Jeff or others add to this theory and explain more fully just how learning takes place and what is the most effective way to cause learning to happen.

Although when I picked up this book I thought it'd be much more about computers then it would neuroscience, this is currently the most well written, clear, and interesting book I've ever read. If you're at all interested in how your brain processes information, or philosophy of mind, or just physiology, this book is for you. I'd recommend that everyone who can read above a 7th grade level should read this just to experience a good example of how difficult, abstract ideas can be expressed clearly, concisely, and in laymans terms.

On intelligence is a good book and an engineer's discussion of how the brain works, processes information and experiences the world. For people wanting to understand how "wet ware" works then this is on the reading list.

The first two chapters are a waste of paper as they discuss Jeff Hawkins personal interest in the subject area -- so skip them. The remaining chapters are a good discussion of the physical properties and processes of the brain. Unfortunately these are presented as forgone conclusions and the final word in brain science, something that Hawkins admits is still really incomplete. Also Hawkins presents the material as if he invented it all, something that detracts from the power of the message.

The discussion is repetitive in places and surprisingly conservative in its outlook -- for example only humans have language, only humans are intelligent. That was a surprise that as the book seems to be fairly open on other issues.

The notion that the neocortex can basically learn anything and has few preconceived notions or hard wiring will provide ample ammunition for behavioralists and those who believe that behavior is learned and not part of nature.

In summary, I found myself skimming much of the discussion on particular ways things work as I can always go back and read it again. This makes for a good book, one that I am glad that I have read, but one that I would not recommend going out of my way to read.

This book advocates a model of how our brain works: human intelligence is predictive pattern matching. When what we predict matches what we observe, we understand. This model is useful in designing workable models for machine intelligence (real intelligence in Hawkin's term), machine learning and machine vision in my case.

I bought this book because of a general interest in human behavior, patterns and intelligence. I have often struggled with verbalizing the differences between how computers and people "think" - and I hoped this book would shed some light on that.

Well it did - but it did a lot more.

Now, this is the kind of material that can either spur the imagination or lay in your belly like 3-day old chili. Of course, that also depends on how (and if) the material connects with you.

The primary point of the book is the presentation of a general intelligence theory based on scientific study of the human brain for the purposes of moving forward the basic scientific principles behind the creation of intelligent machines. Well, I for one am not involved in the creation of intelligent machines however, I see the limitations of current computing technology every single day - as I am an industry analyst for enterprise software.

Regarding the theory itself, I found much of the material had a strong intuitive sense of correctness. Not sure how else one could judge this as it is theoretical. I am convinced that this book did shed clear light on my belief that traditional computing and software will not get us there - that what is needed is an entirely different approach. Jeff presents one that certainly seems plausible.

However, the big takeaway for me was the self-discovery this book triggered for me. On Intelligence has significantly changed my understanding of myself, my behavior, actions, reactions and how I perceive the world. But not everyone will get this from this book, so if you read it with expectation of self-revelation but don't get any don't be surprised.

The ramifications of much of what is presented in this book as it applies to me (I know, that was not the stated intent of the book) are still swirling about - and will be doing so for a very long time.

I have made this book a gift to friends and many have had similar response to mine - but some of not. For people like me, this is an absolute must read. If you read it and don't get much from it then you have learned one thing - you are definitely not like me!

It's just about the right time for a framework to hang our knowledge and questions about human intelligence onto. Hawkins makes a good attempt. I find that a lot of my scattered knowledge and ideas fit onto his framework and a lot of questions become clearer. If the framework sharpens open questions that's good; if current or coming knowledge shows his framework is wrong in small or big ways, that'll be good too. Having this straw man will help keep attention on how things fit together. Just the idea that it's really as simple as he says is challenging.

The writing style aims a little low. At first the book reads as if it will be on a vague popular level without any interesting technical detail or arguments. But after a chapter or two it does get into the nitty-gritty, without being too technical for a layman up to speed on the basics.

These are the main ideas (which he doesn't claim to have originated): The neocortex is what's important. It's organized into a fixed hierarchy of areas with more or less fixed relationships between areas. All the areas follow the same "algorithm," although the tuning varies between areas. The center of the book describes his guesses about the algorithm and how it's wired.

He uses the words "memory" and "prediction" to describe what the cortical algorithm does, and that interferes with his main message that it is more general than that, covering both static and temporal relationships, linear and branching relationships, focused perception and directed action. I recommend making up your own terms for the top-down, bottom-up and sideways processes he's talking about and substitute as you read.

He almost entirely neglects two important things: goal- directedness or backward chaining, and recursive structures (in which, e.g., a sentence can include a sentence, or a prepositional phrase can contain a prepositional phrase). Still I've found it very interesting to try to fit these into or onto his model. Maybe they actually aren't handled by the basic design of the neocortex. Goal-seeking may enter by training from below and pushing from the sides, and recursion may be an exceptional hack (self-looped layers? reification of relationships? a separation into blackboard and manager? echoing off the thalmus?).

If Hawkins fails to mention large areas of research, I think it's because of his sharp focus. He often seems to be describing selected pieces of work he knows more about. I was finally quite impressed with the book.

Ray Kurzweil says that as soon as AI achieves some goal, like beating Kasparov at chess, then that goal gets cast out of the AI orbit.

Hawkins describes a powerful filtering mechanism, based on patterns that are "fed-forward" as pedictions, to enable lower brain regions to sift out the mundane while passing the unusual "up" to the higher brain. As a mechanism, then, so far so good, but not likely to escape Kurzweil's curse.

Presumably the really interesting phenomena happen once the higher brain is reached. It is almost universal amongst intelligence/consciousness theories that the brain does various simplifying pattern-matching tricks, so that some inner goblin can make a choice for you. Dennett, for instance, in Consciousness Explained, has a "concert of the mind", where ideas rear up like loud instruments in an orchestra. Nobody has any idea how that inner goblin works, and you won't find one in this book.

By far the most interesting, daring, and probably the most in error, of all consciousness theories is that presented by the eminent physicist and modern-day genius Roger Penrose, who offers a theorem that consciousness is non-computable, and that its solution is wrapped up in an as-yet undiscovered physics.

I went through this book in one sitting because I couldn't put it down. As someone working in the computer field I found it very interesting providing lots of food for thought. It is easy reading. It is not an in depth look at artificial intelligence but an overview. I found it fascinating.

His logic makes sense to me at least in comparison to many of the other AI articles and books I have read. For example I have read many times that when computer power becomes equivalent to the human brain in processing power we will have comparable artificial intelligence. This just does not make sense to me because even if we cluster hundreds of super computers together and give them 300 years to complete something a human can do in 2 seconds the computers still cannot do it. I don't believe one human has billions of times more hardware power than 100's of super computers unless we are using quantum brains which is a small possibility. The problem most likely isn't hardware it is the strategies the AI engineers are using. I have to agree with the author on this point.

All the authors' ideas may not prove to be 100% correct but I don't believe he claims them to be.

The book has got me thinking and got me excited about AI. What more could I ask for? More detail and being a programmer I wish there was at least one example in code.

Overall I recommend this book as an interesting introduction to AI.

For those who are interested in this field, it is hard finding good books. Many writers are technologist and many of them try to defend positions hard-to-defend (Brooks or Minsky should be good examples). Others are cognitive-psychologist and have bought the merchandise of the first ones about the brain as an information processor (Pinker should be an example of these). Others are essentialists and refuse to discuss the idea of intelligent machines because intelligence is human and that's all. At last, some of them are visionaries like Kurzweil or others.

Luckily, there are writers, coming from technology, philosophy, sociology or whatever, that escape from that classification and it is a real pleasure reading them: Dennett, Searle, Maturana, Varela, Hofstadter, Dreyfuss, Hillis and....Hawkins.

Hawkins has a double background: Technology and Neuroscience. His definitions of intelligence and his explanation about how the brain works and how this knowledge could be used to build intelligent machines is outstanding.

Before reading "On intelligence" and being familiar with the state-of-art in technology, I was convinced that building an intelligent machine was impossible. After reading this book, I am almost convinced that it is possible to build intelligent machines. This is only a matter of time and having people like Hawkins.

The early parts of the book (up to around p 60) were a great read and convinced me to buy the book. But when Hawkins finally laid out his "big ideas", I was deeply disappointed. Hawkins spends considerable space claiming that AI researchers hack up algorithms based on the "how do I do it" approach. He suggests that "real" intelligence requires memory-based hierarchical models.

What is especially frustrating to this AI (specifically vision) researcher, is that Hawkins does not seem to be aware of any AI research that has been going on in the last 15 years, during which data-driven learning approaches have become standard. I was merely suspicious of his ignorance until I checked his bibliography, in which the most recent technical AI citation was from before 1990.

Furthermore, Hawkin's theories on the brain are largely unsubstantiated. He states that his ideas were largely sparked by one dated paper that other researchers have largely ignored - probably for good reason. For instance, he claims that, since different parts of the brain have a similar physical structure, they must function similarly. This is very oversimplistic.

Nevertheless, I did find parts of the book to be entertaining and appreciated his view on the brain's role as a predictor. Although I do not think that I completely wasted my time in reading this book, my time could have been better spent reading something else. Therefore, I recommend this book to non-scientists who want to read about the brain but aren't particularly concerned about the accuracy/usefulness of what they read. Just be a very critical reader and be careful not to be smacked in the course of all the hand-waving!

This is an interesting book, but I'm not at all convinced of most of its major theses. There are way too many statements like "I believe xyz" in the book, and way too few along the lines of "Empirical evidence shows xyz." Hawkins seems to have committed himself to certain dogmas, many of which are probably oversimplifications. For instance, he insists that all the areas of the neocortex are essentially instances of the same software; for a completely contrary view, see Steven Pinker's The Language Instinct and How the Mind Works. Pinker, unlike Hawkins, starts by painstakingly laying out the evidence for the things he really knows empirically are true, and only then indulges in wild speculation.

The best thing that Hawkins can do is (continue to) funnel some of his wealth to real scientists doing real research on neuroscience and cognitive science. Him writing books is not going to help the field.

I came away feeling like Hawkins wrote a book to drum up interest in his company. The company will undoubtedly turn out some tech product that falls (far) short of Hawkins "real intelligence" (a *really* ridiculous choice of words, by the way).

If a nobody had written this book, it might not have been published. If Hawkins had submitted his work (in chunks) to a peer-reviewed scientific journal, I am certin that it would have been soundly rejected for making broad claims with little evidence. Overbroad, overly optimistic claims were a large reason that classical AI was disappointing to many, why neural nets have fallen in and out of favor repeatedly, and why Hawkins interest in cognitive science is worth only the research dollars he can shell out.

The question arises: why would the brain build models of anything? It doesn't matter whether it is a memory and prediction machine or a sausage maker. Efficient causality is not formal causality. I can describe the factory process (the efficient cause) of production of a Ford perfectly but the formal cause--the organization that builds the cars is indispensible. The efficient cause of production would cease without the formal cause ascribed to the corporation. Describing what something does or its efficient causality of operation without tying it to some sort of formal causal identity or a mechanism that doesn't arise all by itself is reductionism. Hawkins describes the process of how it may do some of what it does but he himself admits that the origin of invariant representation (what Plato and Aristotle called Form) is the greatest unsolved question of them all. The goal of all reductionism, as a philosophy, is to show that complex things somehow just are--there is no cause--outside of a self generating web of efficient causes--and reductionists don't want there to be any causes because if there are causes, there are makers. They are all looking for the machine that makes itself--and there isn't any such animal. It is all really very funny. These people are all looking for a causeless cause found in the material world--something a little lower than the God of the philosophers and certainly not the God of Christianity.

Wilhelmson, one of the greatest philosophers of the 20th century described knowing the form of a thing as "becoming the form itself on the plane of the act of knowledge." You know what you know because you become it--you don't know it because the brain is merely mocking up a series of impressions like a camera and feeding them to your sensorium. The whole question of invariant representation without a discussion of previous epistemologies that have attempted to address the issue is sophomoric. Hawkins, like many people thinks that because he has a new take on something that no one has thought about it before.

Jeff Hawkins is "crazy about brains." In this readable book, the electronic engineer combines his training as a computer designer and his self-education into the seat of human intelligence and posits how he believes we can make machine intelligence.

Hawkins believes the major historical mistake of AI is in having ignored the human brain's design and structure. What we need isn't more power (because today's computers run much faster than the electrochemical synaptic reset times of the human brain), but better design. The components of Hawkins' synthetic brain would include the incorporation of time as a function, the recognition of the importance of feedback, and a reckoning of the brain's architecture.

Hawkins is also critical of older AI models which suggested that behavior is the primary indicator of intelligence. He observes that we can be intelligent, quietly, in a dark room. One of my criticisms is that Hawkins observes that we probably have built in to our human brains old code no longer needed; remnants of "legacy code." I'd suggest, though, that one man's "legacy code" might really contain essential, cryptic subroutines. Regardless, Hawkins has great respect for the natural development that has resulted in the human brain.

In short, Hawkins develops his theme as the brain being a repository of data and streams of new input with resulting feedback from which and in which the brain seeks patterns. It's the difference between established patterns, acceptable variants, and new material that makes up the bulk of what our brain does. And it is the anticipation of patterns and acceptable variants that makes up intelligence. I have been a disciple of Doug Hofstadter (e.g. Godel, Escher, Bach: An Eternal Golden Braid) and his "patterns and recursion" look at intelligence for quite some time, so taking a few more steps as required by Hawkins wasn't particularly difficult for me.

The chapter on the function of the cortex was the most difficult and enjoyable for me, with his conclusions and look forward being the icing on the cake. All in all a very enjoyable look at one man's vision for the future of intelligent machines in one nice, tidy, unified presentation.

The author clearly is excited by the mysteries of the brain. As scientists learn more about the brain in coming decades, it seems to me that computers will truly be "thinking machines." They will become conscious.

He doesn't believe our brain is identical to a computer, but rather more like a memory system that makes predictions based on memories. In order to create a thinking machine, we must understand how the human brain really works.

Anyone interested in the future of computers and the mysteries of the mind should enjoy this book.

A fast, fun, fascinating read. Five stars.

I ran into the book in the computer books dept at Borders. Interested, I picked it up, and before long, I was hooked.

Hawkins takes a critical look at A.I. progress, identifies key tactical problems, and turns to the biology for a solution. In the process, the reader learns a lot about cognition, neuroscience, and philosophical implications. Although the book has been criticized as speculative, the book includes an appendix of testable predictions.

The terse and lucid prose makes the ideas accessible, all the while constantly providing tangible, concrete analogies. Hawkins delivers enjoyable and tasty food for thought. You'll find yourself questioning long held beliefs about your own thought processes. Although, having no formal knowledge of neuroscience, and little knowledge of A.I., I question whether Hawkins fairly portrays both sides of the story.

My reading material consists mostly of non-fiction but this book held my attention like a mystery thriller. I just couldn't put the book down until I finished it.

Jeff Hawkins has used his considerable talent of presentation (think of wooing venture capital) to start chipping away at the mystique of human intelligence. I, too, am fascinated with the ideas of intelligence, memory, and consciousness and have been frustrated with the fragmentation of these subjects into artificial (computer) intelligence, neurobiology, and physchology. This is the first time I have seen someone propose even a rudimentary overall theory for intelligence that covers all these aspects and gives a working hypothesis for further study.

One of the insights I especially enjoyed was that input to the brain is essentially the same whether it comes from the eyes, the ears, or any other sense organ. The input is a stream (or multiple stream) of bits which must be interpreted by the brain in light of it's past experiences. That explains so much about sensory compensation in the blind or deaf and even the phenomena of people "seeing" sounds or "tasting" colors which I have read in other books. It also points the way for the medical community to treat sensory deficits such as blindness or deafness.

New to me was the fact that neural messages coming from the brain to sense organs (feedback) are usually, if not always, more extensive than the messages from sense organs to the brain. If this is so, it is completely ignored by all the other books on intelligence that I have read. But it makes perfect sense in Jeff's concept of intelligence.

Could have used more and better illustrations but still a wonderful read.

I suspect that Jeff Hawkins has bruised a lot egos and violated protocols with his hypothesis about the human cortex. He offers his idea along with many useful analogies so that one doesn't get too lost along the way. He makes a conscious effort to bring as many people as possible along with him to understand his first best guess on the brain's ability to remember and predict.

It is the highest sign of an authors's intelligence when he can express complex concepts in a cohesive and understandable manner.

After reading this book thoroughly, you will begin to analyze some of your own behavior (thoughts and actions) in relationship to the prediction machine he describes. It is fascinating.

I have to give 4 stars because the illustrations are pitiful. I don't understand why he decided to scrimp on illustrations. By brain really missed some comprehensive diagrams to speed my understanding.

On Intelligence is a fascinating theory of the neocortex - the seat of human intelligence. Jeff and Sandra present a detailed and credible account of the mechanics of the neocortex and show how (and argue why) their predictive memory model results in intelligence. Their theory is elegant and, even though far from complete, I am thoroughly convinced that it is a decent approximation of what goes on in the brain. Biological machinery is extremely simple, it only seems fantastically complex due to properties that emerge at scale. Authors build on the premise that every cell in the neocortex runs the same algorithm and intelligence is an emergent product of this neocortical algorithm. Read this book - it will no doubt be considered one of the most important works of our time. If you have a machine learning background, check out Dileep George's paper on invariant representations in the visual cortex. Dileep is a colleague of Jeff's (and they recently founded a company together called Numenta) who is already converting insights from the research into efficient algorithms.

I read the whole book and was very disappointed. If you want to stand on the shoulders of giants, that is, learn what objective experts have been able to intelligently hypothesize based on extensive well-grounded knowledge and research, then DO NOT read this book. I found the authors claims to be wildly speculative, doubtful and overly simplistic. The author seems to have a grudge against the research community which is perhaps why his claims seem so dubious. His "the research community doesn't know what it's talking about, I do and he're _MY_ idea" attitude is unfortunate, immature and annoying. I can not recommend this book.

I've been programming computers for so many years, and if there's one thing I KNOW for sure, computer books are BORING! Ahh, but this isn't a computer book, and I found it engaging enough to read all the way through.

I know nothing of AI nor of how the brain works, yet I liked this book, except chapter 6 "How the Cortex Works"...ugh, this part made my head hurt!

This is not a "How To Program AI" book. To me, it's a book about another way to view the Brain/Intelligence/AI puzzle, another way to look at the problem, if you will.

Was it a good book regarding computer Technical information? Umm, I don't know, most likely not, but that's ok.

Was it a good book regarding understanding the Brain? Umm, I don't know, but I think it was a good overview of some therotical wokings of the brain.

Most importantly, did this book serve to increase my interests in AI and Human Intelligence? Absolutely YES! The ideas presented in the book sparked my imigination and curiosity, while at the same time let me know without ANY doubt that I need to study this subject much more!!!

I found the reviews and blurbs very intriguing, and once I had the book I didn't put it down until I had read it all.

This book does *not* have the kind of science-is-wonder attitude you might find in Sagan; it does not convey the message "Study science, it's a noble thing to do, your curiosity will be greatly rewarded", like some reviewers write. It's not the kind of book that summarizes the state of what's known about the brain today, while getting you excited about finding out more.

This book is really a monograph by someone who thinks they have literally figured out the brain, and it contains mostly what the author has to say. So you won't see a mention of the holographic theory of the brain, or the brain-as-dynamic-system view. In my opinion, in a book addressed to the general public, that's a problem.

It's a problem, because on one hand the book is written for the general public, while on the other hand it presents utterly untested (by anyone, even the author) hypotheses, mostly made by the author himself or hand-picked from existing research.

In this respect, it reminds one of "A New Kind of Science" by Stephen Wolfram, another "scientific" book which aims to directly impress the layman with something he's not likely to understand, while bypassing specialists.

Next, what annoyed me somewhat is the the fact that the subject, admittedly the biggest mystery of our time, is given such a simplistic treatment. No, we're no closer to creating something that can, say, semi-intelligently fly around the room and land on things, or since the author prefers non-behavioral intelligence, detect whether a given picture has a cat in it. So why such extraordinary claims of no results were obtained?

Finally, there is no evidence that the author or his colleagues have actually built any software or hardware that can detect any meaningful patterns in visual or audio streams.

Yet, I'd still recommend this book, because it highly readable, and it'll make you think (even if it's about the outrageous claims). Because of that it gets four stars.

I found the reviews and blurbs very intriguing, and once I had the book I didn't put it down until I had read it all.

This book does *not* have the kind of science-is-wonder attitude you might find in Sagan; it does not convey the message "Study science, it's a noble thing to do, your curiosity will be greatly rewarded", like some reviewers write. It's not the kind of book that summarizes the state of what's known about the brain today, while getting you excited about finding out more.

This book is really a monograph by someone who thinks they have literally figured out the brain, and it contains mostly what the author has to say. So you won't see a mention of the holographic theory of the brain, or the brain-as-dynamic-system view. In my opinion, in a book addressed to the general public, that's a problem.

It's a problem, because on one hand the book is written for the general public, while on the other hand it presents utterly untested (by anyone, even the author) hypotheses, mostly made by the author himself or hand-picked from existing research.

In this respect, it reminds one of "A New Kind of Science" by Stephen Wolfram, another "scientific" book which aims to directly impress the layman with something he's not likely to understand, while bypassing specialists.

The author generally has a dismissive attitude towards others' research, as if it doesn't matter. But it does. For example: a real neuron is, to say the least, unreliable. It can fire without having the right inputs, or not fire even it has the right inputs. It's noisy. But this fact isn't mentioned in "On Intelligence", because it undermines the author's idea that an individual neuron serves as a "name" for a "current sequence" in the brain.

What annoyed me the most is the the fact that the subject, admittedly the biggest mystery of our time, is given such a simplistic treatment. No, we're no closer to creating something that can, say, semi-intelligently fly around the room and land on things, or since the author prefers non-behavioral intelligence, detect whether a given picture has a cat in it. So why such extraordinary claims of no results were obtained?

There is no evidence that the author or his colleagues have actually built any software or hardware that can detect any meaningful patterns in visual or audio streams.

Hawkins gives a nice, easily digestable synthesis of the fundamental architectural elements in the human mind. His ideas are built upon the recognition, by Vernon Mountcastle, that the neocortex appears to be doing a similar process whether it is processing visual, auditory, tactile or any other sort of information. That recognition forms the basis for a very elegant proposal regarding brain architecture.

The author has made a pitch to high school students to interest them in studying creation of intelligent machines. With the objective of interesting high school students, the level of detail and rigor is probably appropriate. Some book-related websites have been created, most notably www.onintelligence.org.

When aiming at a general audience, it is not reasonable to apply criteria appropriate for a scholarly work, although once interest is excited one naturally asks for greater elaboration. So I think some negative reviews are based on disappointment that the author doesn't go further, more than any defect of the book. For me the most interesting parts of the book are the illustrations of how the author does futuristic thinking.

My rating is based on interest and provocativeness. I think that is the right basis for assigning a rating in this instance.

This is a wonderful book. I think perhaps its most significant contribution is "Connectionists have been too timid."

Pretty much each of the objections raised by other reviewers are dealt with in the early chapters.

The analogy the authors draws with alien explorers of a post-extinction earth is important here. Their examination of the road system might generate a LOT of specific data that doesn't make much sense until you realize: humans can't teleport, they used roads for travel. Almost all of the details of the roads gathered would be incidental, accidents of geography - the unifying concept is understanding the purpose of roads.

In the same way, his unifying theory of how intelligence works in the brain is that intelligence is a memory-based prediction mechanism. If you plug that mechanism into visual input areas, you will get understanding/intelligence about visual data - that pattern of light varying over time and through space is a brick heading towards your head, so you should probably duck since your somatosensory intelligence strongly disapproves of the most likely outcome.

He cites several lines of evidence for this theory. The part of the brain responsible for abstract reasoning, higher thought - it has a very uniform structure that is differentiated mainly by the sensory subsystem it is connected to (bidirectional connectivity). Further, the subsystems can be interchanged somewhat - if no visual sensory input is available, the areas typically tasked with visual understanding can take over (with reduced efficiency) for auditory or somatosensory understanding.

Further evidence: the input, the action potentials transmitted across synapses, seems to be relatively undifferentiated across domains. When you see a bird flying, you don't get a reverse image in your mind: that light data is converted into action potentials that are transmitted to your visual cortex (V1) and through a bidirectional, feedback intensive process - this info becomes visual intelligence (the thing you're seeing is a bird, it is flying, etc...). This uniform translation of sensory input into action potentials lends itself for manipulation by a unitary kind of algorithm/processing (his theory of intelligence).

It is unsuprising that it would take a Computer Scientist (like Jeff Hawkins) well versed in Neuroscience to come up with one of the most compelling theories of how the brain creates intelligence. Figuring out algorithms is what CS types do. That plus they're more likely to be unspoiled enough by the trees to grasp the beginnings of the forest.

All in all a great book!

This is a wonderful book. I think perhaps its most significant contribution is "Connectionists have been too timid."

Pretty much each of the objections raised by other reviewers are dealt with in the early chapters.

The analogy the authors draws with alien explorers of a post-extinction earth is important here. Their examination of the road system might generate a LOT of specific data that doesn't make much sense until you realize: humans can't teleport, they used roads for travel. Almost all of the details of the roads gathered would be incidental, accidents of geography - the unifying concept is understanding the purpose of roads.

In the same way, his unifying theory of how intelligence works in the brain is that intelligence is a memory-based prediction mechanism. If you plug that mechanism into visual input areas, you will get understanding/intelligence about visual data - that pattern of light varying over time and through space is a brick heading towards your head, so you should probably duck since your somatosensory intelligence strongly disapproves of the most likely outcome.

He cites several lines of evidence for this theory. The part of the brain responsible for abstract reasoning, higher thought - it has a very uniform structure that is differentiated mainly by the sensory subsystem it is connected to (bidirectional connectivity). Further, the subsystems can be interchanged somewhat - if no visual sensory input is available, the areas typically tasked with visual understanding can take over (with reduced efficiency) for auditory or somatosensory understanding.

Further evidence: the input, the action potentials transmitted across synapses, seems to be relatively undifferentiated across domains. When you see a bird flying, you don't get a reverse image in your mind: that light data is converted into action potentials that are transmitted to your visual cortex (V1) and through a bidirectional, feedback intensive process - this info becomes visual intelligence (the thing you're seeing is a bird, it is flying, etc...). This uniform translation of sensory input into action potentials lends itself for manipulation by a unitary kind of algorithm/processing (his theory of intelligence).

All in all a great book!

This book is stunning in both its scope and focus. I'm not a practitioner but have been interested in the field of neuroscience for many years; read Restak's first edition in the early 80's. Hawkins brings dimensions of the subject together in a very simple and understandable way so you immediately grasp the magnitude of his memeory prediction model of intelligence. It will get you thinking.

I read this book to find out more about how consciousness works. I got that and more.

Jeff Hawkins presents a working, testable mechanism for how intelligence occurs in human brains. More than that, his mechanism has the potential to be built electronically into helpful intelligent machine applications. His exposition on his model of intelligence is quite readable and he makes technical points using everyday examples that leave you going, oh, so THAT'S what's going on.

Hawkins explains how he moved from practical computer science (co-founder of the PalmPilot) to practical brain science (founder of Redwood Neuroscience Institute) and invites young people in high school and college to jump on board. He communicates freshness and excitement about creating a new thing in the world that I last experienced reading the biograpy of Amazon.com founder, Jeff Bezos.

I recommend this for anyone interested in how intelligence works, whether it's to better understand people, design cool new technology, or just because.

While I am a novice to this area, I think that that the book made me interested enough to dig deeper. I'm not convinced by Mr. Hawkins claims that his model explains consciousness because what he described as consciousness is not what I experience - and in fact I found that this was the weakest part of the book.
However, the book makes a brilliant read and if the reader walks away with the idea that the architecture of the brain may actually be quite simple - or based on simple elements then I think the reader has gotten the point.
In a nutshell Mr. Hawkins elucidates upon Vernon Mountcastle's theory of the brain and adds some of his own ideas about hierarchy and feedback - none of which sound unreasonable and could lead to some novel devices. Only time will tell whether this is *the* theory of intelligence, however.
I would at the very least say that the book is essential reading for those interested in computational neuroscience.

Most of the other reader reviews tend to fall in to one of two perspectives, either "Cheerleader" or "Nothing new here, move along". Some readers are put off by the lack of academic rigor, paucity of research citings, and vague illustrations. Hawkins himself recognizes in the last chapter that this is not an academic paper, but an effort to make the concepts of the brain and their possible application to future artificial intelligence systems understandable to the laymen. He hopes that some of the more ambitious readers who are still deciding their life work will choose to pursue this area of study.
The complaint about the graphics is right on I believe, though it seems that the art of illustration has largely left the printed media. Certain chapters in this book would be greatly enhanced with 3-d renderings and even paper pop-up models as someone else suggested.
I also think that Hawkins wrote in a form that simulated the structure and operation of the cortex he was trying to explain. That is, he seemed to introduce broad, vague concepts with lots of feed-forward references to later, more detailed explanations. In trying to make the complexity of regions, layers, columns, neurons, synapses, dendrites, axons, etc more accessible, he attempted to drive our auto-associative patterns, placing specific information into previous, general patterns...I think.
The real downfall of the book I believe is when he assigns all of human characteristics and behavior to the complex, highly evolved but ultimately mechanical processes of the brain, leaving no room for metaphysical explanations. "There is no special sauce" he says, just electro-chemical operations in the brain. Gosh, Jeff, good thing you clued us in on this. Maybe there's still time for the Pope to find a new career! With a single paragraph, Jeff dissed billions of people of hundreds of different belief systems that expect that there is a personal existance long after the brain stops functioning.
I guess I'm just not ready to write-off the possibility for divine intervention. Even Einstein admitted that, at some level, God plays a role. And Jeff, you're smart, but you're no Einstein.

FWIW,
Jason

It is pretty clear that there are two classes of reviews for this book. One class, typically written by lay people, believes it to be the best research available on how the human brain truly works. Scientists, however, view the book a bit differently.

I am a researcher in robotics and specialize in developing control systems for autonomous robots. My company builds robots that can move around, and that have arms with which to pick up objects, all working without human control. Vision and touch are the senses used by our machines, combined with biologically inspired computer algorithms, to get the job done. Most of my work, like that of Mr. Hawkins, focuses on thinking about how animal brains might work and applying those thoughts to real systems.

I believe that Mr. Hawkins is a very sharp guy, and he describes his ideas about how the brain works with great clarity. He is outstanding at creating buzz. But, with all due respect, I believe that he doesn't even know what he doesn't know when it comes to building systems that work in the real world. The book reads as if the theories espoused are based on science, but they are really based on the author's conjecture. True, it is reasonable conjecture, but not fact. Software reportedly has been written based on these theories that is capable of recognizing hand drawn objects. I have not found any papers to review concerning this technology, but similar technology (e.g. OCR) is already available that is robust when recognizing hand drawn characters so this is not yet a tremendous breakthrough. Basically, working with 2D images is relatively easy, working with a computer generated 3D world is 10x harder, working with real imagery in a constrained environment (in a lab with controlled lighting, etc.) is 10x harder still, and working outdoors in the real world is about 100x harder than that. Current technology for autonomous robotic control and object recognition is not based on techniques of classical AI, but is in fact based on pattern recognition/matching techniques essentially similar to what Mr. Hawkins proposes, including the idea of prediction.

On the one hand, I applaud the author if this book inspires other people to enter the field. On the other hand, readers are cautioned that this is a "popular science" book and does not represent any great breakthrough.

Jeff Hawkins' day job has been the creation of the Palm Pilot and the Handspring Treo, along with the Grafitti writing system used on those devices. His "hobby" - and a very serious one it seems from this book - is studying how the human brain works.

Hawkins has been bothered by the lack of a unifying theory of what the brain actually does that makes it intelligent and the absense of a good book on the topic for the lay-person. On Intelligence is his response to those concerns. The book is one big hypothesis on what is going on inside all of our heads that separates us from even the fastest computers. The crux of the issue is that our brains are pattern storage and pattern recognition devices that use those two functions to incessantly make predictions about what is coming next in the world around us.

The evidence and explanations that Hawkins offers up are compelling and fascinating and his theory conceptually makes sense when you think about it. In the end Hawkins happily admits - and we as the reader need to remember - that what he is doing is offering up a hypothesis for science to work with, prove and disprove as the study of the human mind advances.

Highly recommended for the interested lay-person by an interested lay-person.

I have always been curious about how the brain works, and why it can do things that computers that work a million times faster cannot begin to achieve. I thought this book might be too difficult for me because I am not a scientist, but it was not compicated. It tackles what I used to think must be an infinitely complex subject in a simple and interesting way for the average person, through great writing, common sense explanations and simple analogies. They do an excellent job of avoiding getting into the details that confuse and bore non-scientists. I started reading it out of curiosity, and then I could not put it down. If you have a brain, hope to have a brain someday, or have any interest at all in how brains work, you should read this book!

In his now classic work, The Computer and the Brain, the late Jon von Neumann constructed a systematic point by point comparison of the brain against what was almost universally viewed as it's artificial counterpart; the computer and despite first being published in 1956 it has remained the seminal work on this subject - until now. That almost fifty years lapsed before a work emerged whose thoroughness and revolutionary nature provides serious challenge to accepted dogmatic would be an insight into the neglected state of affairs of any field - when this is further compounded by the technological explosion in personal computers and the wealth of data we have just recently been able to begin harvesting about the brain it makes for an almost criminal indictment against all those prior to Jeff Hawkins who were content not to question the accepted view of the brain as being essentially a computer.

It is exactly these two subjects of brain and computer that Hawkins acknowledges as being the twin passions animating his writing of On Intelligence. Such passion is truly evident in both his chronicling of how he came to hold these views as well as in his detailed explanations of what his new understanding of the brain's inner works are.

One's heart must go out to a writer who is unafraid to put forth grand ideas even as they freely acknowledge that all the evidence is not in yet. Like Einstein waiting for his conformation that starlight is bent when passing too close to the sun, Hawkins too is confident that in time as we are able to fill in the missing puzzle pieces it will all fall in line as he has predicted.

This is a great book, written with heart and passion and is sure to cause readers to see the brain (and themselves) in an new light!

Jeff Hawkins presented a credible framework for anyone interested
in understanding intelligence and actually trying to start
implementing it, although "intelligence" is not something that
can be fully explored in less than 300 pages and Jeff admitted
that he does not have answer to everything in the topic. Being
a graduate student in AI field in the 80's, I share a lot of
frustration the author felt over the years. A workable frame is
what we badly needed to jumpstart an almost dead field.

I see it as a practical way to proceed. Jeff Hawkins may
well be the next Wright brothers!

In the field of artificial intelligence it seems there are as many definitions of intelligence as there are stars in the heavens. Each of these definitions seems plausible, and interestingly, they seem to get more difficult to satisfy with time. Thus progress in artificial intelligence seems to be non-existent, since the criteria used to designate a machine as being intelligent ten years ago are no longer used today. Researchers in AI used to believe for example that if a machine could beat a human in chess then it should definitely be deemed intelligent. That belief is hardly held by anyone in the AI community at the present time.

The author of this book proposes yet another definition of intelligence, and it is one that is inspired by his understanding of how the human brain functions. His justifications are interesting, but they are highly speculative, and border on mere philosophical musings. It would have been a better book if the author refrained from the random walks in conceptual space that are characteristic of philosophy, and justified his conception of intelligence with what is really currently known in neuroscience. He does quote the research of neuroscientists that have produced a detailed map of the monkey cortex, which revealed many different regions connected together in a complex hierarchy. The author then makes the assumption that the human cortex hierarchy has a similar hierarchy. This is not really an unreasonable assumption if viewed from the standpoint of neuroanatomy, but from the standpoint of the cognitive abilities of humans versus those of monkeys, it might indeed be an assumption that deserves intense scrutiny.

The author definitely wants to view intelligence as being one that can function over many different domains, i.e. an intelligent machine will be able to not only play chess for example, but could also analyze stock market data or perform some other function typically thought of as requiring careful thought. He expresses this by saying that the human cortex is "universal" in that it can be applied to any type of sensory or motor system, and that the "algorithm of the cortex" can be expressed independently of any particular function or sense. Certainly humans can think in many different domains, but one cannot conclude from this that humans possess the general intelligence that the author believes they do. There is in fact a large body of research that indicates that the human brain has a modular structure (the author discusses this research very briefly), with each module being responsible for functioning in a particular domain. If one of these modules ceases to function, this has no effect on the functioning of the others. This is a view of the brain as having a domain-specific structure. A domain-general notion of intelligence would mean that the brain can deal with several different domains, but that the same reasoning patterns or processes are used to think in these different domains. If one of these reasoning patterns or processes becomes non-functional, the rest of them will suffer. One could still view the brain as consisting of modules expert in different domains, but that these modules are "entangled" with each other in the sense just specified, i.e. damage in one module will affect the others.

In fairness to the author, there is also research in neuroscience that lends support to his notion of general intelligence and a single algorithm that can deal with all of the data presented to the human brain. He gives a few references that discuss this research, and he definitely emphasizes the need for feedback and the related notion of `auto-associative' memories. The brain in his view is a "pattern machine" and if one is to construct truly intelligent machines one must make use of this pattern manipulating capability of the human cortex. Thus intelligent machines will be a result of this "neocortical inspired" computing, and the author spends a lot of time explaining why these machines will mimic the ability of the brain to solve a problem using memory, and not by computing a solution. The cortex, in his view, creates "invariant representations" which can handle the intricate variability of the world it is confronted with. He summarizes this viewpoint by saying that the neocortex stores sequences of patterns, recalls patterns auto-associatively, stores invariant patterns, and stores patterns in a hierarchy. His explanations of how it does this are interesting, but again are very speculative, and in the absence of a prototype for a machine that possesses this kind of intelligence, it is difficult to assess the validity of his assertions.

This reviewer strongly disagrees with the assertion from the author that there are no machines today that express true intelligence. A strong case can be made for the existence of myriads of intelligent machines in the world today, but this case would again be dependent on a particular definition of intelligence. Machines that have intelligence as the author defines it are nowhere in sight, and this is no doubt due to the lack of commercial value in the domain-general intelligence that the author advocates. The intelligent machines of today can learn, adapt, and manage, and do many other different things, but they only do these things in specific domains. There is absolutely no need for these machines to have expertise in more than one domain, both for the sake of efficiency and also because of economics. In managing a network for example, there is no need for a machine to have expertise in some other area, such as chess playing or backgammon. Business demands thus dictate the kind of domain-specific intelligence that is so prevalent in hundreds of intelligent machines performing many useful functions in business and industry.

On Intelligence, either you agree with Jeff Hawkins point of view or not, is an interesting or informative read. Jeff promotes the idea that intelligent machines can only be created by understanding and replicating the way human brain works. He argues that current models of artificial neural networks, statistical learning and decision support systems aren't truly intelligent; the vision of intelligence is beyond mere data processing and thinking creative doesn't come from learning models evolved from this thinking. This challenges almost the entire foundation work of Artificial intelligence and depicts a new paradigm for machine learning. I recommend all CS/EE related people to read it.

-Adnan Masood
MSc. MCSD.NET
www.axisebusiness.com/adnano

There was plenty of buzz last week about the new company - Numenta - that Jeff Hawkins (inventor of Graffiti and the PalmPilot, Visor, and Treo products) and Donna Dubinsky (CEO of Palm and Handspring) have started. It was coincidental that I was reading Hawkins book - On Intelligence - which describes his theory of intelligence, the working of the brain, and how he thinks it will lead to the creation of truly intelligence machines.

I haven't spent any time studying neural science, the brain (my biggest effort was probably not very successfully grinding through the Scientific American issue on Better Brains), or any of the contemporaneous efforts at "next generation Artificial Intelligence" (I was at MIT in the 1980's during the peak of the last wave of AI research and subsequent commercialization attempts - I fondly remember being amazed at Symbolics - they are still around in a new incarnation called Symbolics Technology - Macsyma has been hard to kill off) .

So - I don't know much about brain research, theories of intelligence, the biology behind it, or much of anything else. As a result, I thought On Intelligence was superb. I don't expect that it's right (nor does Hawkins) - he's clear that it's a framework and work in process (as it should be). I found it extremely accessible, very provocative, and mostly internally consistent (which is important whenever you are trying to learn about something you know very little about - it can be wrong, but at least it hangs together in a way you can understand it.)

The book and theory is based on the work being done at the Redwood Neuroscience Institute, of which Hawkins is the founder and director. Beyond just doing research, part of RNI's mission is to "encourage people to enter and pursue this field of research." Hawkins is consistent in his message in the epilogue of his book where he says "I am suggesting we now have a new more promising path to follow. If you are in high school or college and this book makes you want to work on this technology, to build the first truly intelligent machines, to help start an industry, I encourage you to do so. Make it happen. One of the tricks of entrepreneurial success is that you must jump head first into a new field before it is one hundred percent clear you can be successful. Timing is important. If you jump too early, you struggle. If you wait until the uncertainty lifts, it's too late. I strongly believe that now is the time to start designing and building cortical-like memory systems. This field will be immensely important both scientifically and commercially. The Intels and Microsofts of a new industry built on hierarchical memories will be started sometime within the next ten years. It is challenging doing new things, but it is always worth trying. I hope you will join me, along with others who take up the challenge, to create one of the greatest technologies the world has ever seen."

Hawkins thoughts and writing are fused with his obvious entrepreneurial energy. He approaches things as an ultimate pragmatist (unlike so many scientists, his examples and analogies are extremely understandable - very reminicient of Richard Feynman), an outsider (he acknowledges that mainstream brain research has huge problems with many of the things he is saying), and recognizes that any fundamental breakthrough typically requires a paradigm shift in thinking about the specific domain.

If you are an entrepreneur who likes to challenge yourself intellectually with things you know nothing about, you'll love this book. If you are a brain researcher or scientist, you'll probably be frustrated, but it'll stretch you in good ways. If you are a brain expert, you'll probably hate it. In any case, it'll be fun to watch what Hawkins, Dubinsky, Numenta, and RMI do next - remember, they're the ones that brought you the Palm Pilot / Handspring Treo based on the revolutionary notion that humans should learn to write different (e.g. Graffiti), not the ones that brought you the Go Whatever or the Apple Newton who thought that the computer should be able to recognize your handwriting.

Naive and speculative. The author is right criticizing neuroscience and AI, but the rest of the book is pure fiction without any arguments supporting it

If you've ever thought about thinking, and wondered how billions of massively interconnected neurons can simultaneiously do things like process sound, vision, touch, smell, decipher language, wonder about things...then this book is a must read.

The authors present an elegant and clearly articulated theory for how the neocortex works its wonders even though the communciation speeds between its elements (neurons) are millions of times slower than digital computers that can't do any of those things.

This book presents strong arguments that prediction is a more important part of intelligence than most experts realize. It outlines a fairly simple set of general purpose rules that may describe some important aspects of how small groups of neurons interact to produce intelligent behavior. It provides a better theory of the role of the hippocampus than I've seen before.
I wouldn't call this book a major breakthrough, but I expect that it will produce some nontrivial advances in the understanding of the human brain.
The most disturbing part of this book is the section on the risks of AI. He claims that AIs will just be tools, but he shows no sign of having given thought to any of the issues involved beyond deciding that an AI is unlikely to have human motives. But that leaves a wide variety of other possible goals systems, many of which would be as dangerous. It's possible that he sees easy ways to ensure that an AI is always obedient, but there are many approaches to AI for which I don't think this is possible (for instance, evolutionary programming looks like it would select for something resembling a survival instinct), and this book doesn't clarify what goals Hawkins' approach is likely to build into his software. It is easy to imagine that he would need to build in goals other than obedience in order to get his system to do any learning. If this is any indication of the care he is taking to ensure that his "tools" are safe, I hope he fails to produce intelligent software.

James Watson, one of the winners of the Nobel prize for discovering DNA, praises this book. So, who am I to think it's so bad? No one really, I have no education, training, or specialization in any of the areas discussed in this book so maybe the problem is me, not the book. But, the book is billed as if written for laypersons, not experts in the field. So I'm more the audience than Dr. Watson, and I found it lacking.

I have no idea id any of Hawkins' theories are correct or not. Having read the first half of the book though, Hawkins had failed to offer any proof that any of his theories are correct. He beats them to death with some analogies, repeats conclusions from hypothetical experiments as if they have been laboratory tested, and then moves on to build on this very shaky foundation. About half way through the book when I realized that he was done laying the foundation, wouldn't offer any proof, and was now squarely in the middle of building his conclusions, I put the book down.

While the book may be important in terms of forward-looking hypothesis, it doesn't do anything to support the claims the author is making. It's as much science fiction as science, as it's all speculation, little proof.

I did skim to the end to find the appendix that in my mind, really proves my dissatisfaction with this book is well-founded: "Testable Predictions." Until some of those tests can be performed and prove or disprove his theories, this book is premature. Unlike a theory in another scientific discipline (physics for example) if the theory can't be backed up experimentally, there's got to be some good grounding to prove it and rule out other theories from another standpoint (in the physics example, a theory has to work mathematically to be worth experimental testing). In his theories, there is no other outside frame of reference given to try to prove them.

I strongly believe this is the most important research paper that has come out in recent times. Unlike any other dry and cold papers you may have read, this one is written in very personal and engaging style.

The author points out what is missing in current AI research and why theories such as neural networks are not sufficient to realize truly intelligent systems and then he goes on to establish the need for understanding exactly how brain works, his struggle to assimilate this knowledge and establishing a need for a framework for understanding the intelligence that comes along with biological brain.

I read a lot of original scientific papers - from Einstein's original relativity papers to Maxwell's 3rd paper to Newton's Principia and so on and if all these works were published the way Jeff Hawkins published his On Intelligence, the world would be a different place, with possibly more then half the population knowing what General Relativity is all about :). The most important element of Jeff's writing style, which I believe some of the greatest works in science do not have, is that Jeff walks you through his thought chains rather then just describing and formally justifying the end results of the thought chain. This is exactly the kind of work I was looking for a long time.

On the negative side, many people would raise their eyebrows if I insist calling this book as a research paper because it lacks technical accuracy, structure and overall strength. The author doesn't bother about "mathematising" his framework. This is a HUGE weakness and just that fact alone can cost its formal acceptance in the field. The book solely tries to survive in English description of its founding ideas.

Another weak point of the book is the pages and pages of repetition and redundancy in describing key concepts and that can really get you tired. The book strongly lacks structure which can just make you feel clueless about what you read so far and what to expect next. In my second pass reading, I always keep a pencil with me and underline the key points that author is making so I don't have to read those tiringly repetitive pages again to come to a point. My assertion is that the book could have been written in 10 pages without missing anything important or loosing its informal style. That's another bad thing: this one of the most important paper is available only if you are willing to spend money to buy it as a printed book. Do all these authors forget about the existence of Internet for sharing and collaboration of their works instead of locking it up exclusively inside expensive magazines and books that only academia has an access?

The presentation quality of the book is probably its next biggest weakness. This book could have used popup boxes like those modern technical books, bullet list of facts, many more diagrams, content divided in to logical hierarchical sections, each chapter ending with summery, what to expect next, references, bulleted list of unanswered questions for that section and so on. The readers who really want to research on authors ideas and write prototype have to carry the burden of filtering redundancy and structuring the content.

The book also has companion website where you can find some work from a guy from Stanford, Dileep Geaorge, in formalizing author's ideas and even a working software prototype (however from the first look I felt as if it's merely an extension of Bayesian networks and HMM rather then actually putting author's thoughts in structured form and mathematical grounds). There are obviously many missing links but I've hardly any doubts that the direction that this paper establishes is the right direction.

Mr. Hawkins will be the first to admit this is not a book to explain everything about intelligence but an important first step. He puts forward a rational explanation of how intelligence in man works in practical mechanical terms. It is a theory but he has much to back-up his conjectures. His theory gets the ball rolling for a frank discussion of why, how, and what we really doing in our mind when we think. He avoids general behavior and philosophical musing about the human mind (that we are all to often inundated with on books about intelligence). I enjoyed every bit of it. At the very least you'll enjoy he very different approach to this age old question.

This book is a really great start to addressing the problem of how we humans think. Good job Mr. Hawkins.

This book is well worth the read. You'll find it engaging and the pages should turn quickly. Chapters 1 thru 5 are very easy to understand and during this part of the book you will think the book is all about brains and what constitutes intelligence. Then there is chapter six. Chapter 6 is highly technical even for me (I consider myself a fairly smart and technical kind of guy) and I will admit that I skipped it about ten pages in. Then, in chapter 7, you will discover that this book is pretty much concerns everything... every subjective quality of existence that makes being human what it is to you and I is described. I will venture to say that I found chapter seven enlightening. I'm not a scientist; I picked this book up because I'm of the smartypants type that reads such books for the mere pleasure of it. I think that everyone could learn something very profound from this book, even (and especially) the non-technical. Now, you have to read the preceding chapters to enjoy chapter 7, but that shouldn't be a problem, I found them quite interesting. I'm just saying that the value of this book is almost exclusively in chapter 7; at least it was for me.

The remainder of the book is what I really bought it for, and that's the part about building intelligent machines, which was great. I think when most buy this book, they think that is all that they are getting. Quite a pleasant surprise it was to be enlightened about all human existence. Just read it.

I still can't understand why this book didn't catch any buzz on modern socities. You can actually grasp the idea that the suggested memory prediction framework is the reality that is going on inside your brain when you read more and more. On every page I found myself like "Exactly..Now I can see...".

Another interesting positive effect of the book on me is the belief that we don't have to leave AI to CS grads and alike. As an architect, I started to believe in me that I can create my own memory-prediction system.

The accolades previous reviewers have lavished upon this book are all fully deserved. It is not, however, "the first time all these bits and pieces have been put into a coherent framework". The work of Stephen Grossberg explored all of these themes in the 1970s. Unfortunately Grossberg expressed his key insights in systems of differential difference equations that few could understand and fewer still could build upon or contribute to.
To his credit, Hawkins does cite Grossberg approvingly at several junctures in his argument, but he fails to take into account several of Grossberg's greatest insights into neocortical processing: his theory of how serial processing can be accomplised in a parallel anatomy and his theory of "rebounds". The latter is especially important since it explains how new memories are prevented from overwriting old memories. For example, when I learn a second language, it doesn't overwrite my first.

These criticisms, however, are in no way meant to detract in the slightest from Hawkins' superb book. It is an eminently readable account of neocortical computing, and correct in all its broad brush strokes. If you are as beguiled by "On Intelligence" as the other reviewers in this thread, my purpose is only to alert you to the even deeper wonders that are to be found in Grossberg's work. As I have said, his work is difficult, but his 1980 and 1982 Psychological Review articles will provide good entry-points. Those of you with an interest in brain and language will find an even better second course in neocortical computing in Loritz' "How the Brain Evolved Language" (Oxford University Press, 1999).