Customer Reviews
An Intelligent and Readable Book on Intelligence - By: Steve S., 10 Aug 2008 
Jeff Hawkins is the founder of Palm Computer, & the inventor of the Palm Pilot & Treo. After making his fortune, Hawkins turned his attention to neuroscience. Given that history, I was afraid that this book was only published because Hawkins is rich, successful & presumed smart. In fact, Hawkins is smart. More importantly, he has some very good ideas about how the brain works, & he presents themin a clear & concise way. This is an excellent book.
Hawkins presents a theory of how the brain makes predictions. Questions that are easily solved are solved at a lower level. If they cannot be solved, they move up to the next level -- something like. I'll let Hawkins explain it. He does a much better job.
"On Intelligence" could easily have been titled "How the Mind Works." In fact, that title is taken by another wonderful scientist & writer, Steven Pinker. The two books have very littlein common after that. I highly recommend both.
Valuable source of information - By: Ahmet Tekelioglu, 11 Jun 2007 Mr Hawkins has given a lot of thought to the question of building truly intelligent computers & it shows. Chapter 6 is a detailed account of his findings, where he identifies the fundamental issues involved. The other chapters are much easier to read. Had Mr Hawkins provided a more comprehensive list of references, it would have been better for the readers who plan to read further. Even so, since most of the fundamental issues at hand appear to have been discussed, this book is an eye-opener. It should be of interest to computer scientists & neurologists alike.
Intelligent Read - By: , 08 Apr 2005 I don't know why I bought this book, but maybe I just wanted to read something different. I've read a lot of books about physics & science & thought I'll give this one a go. The explanations about the concepts of cognitive thinking was convincing.
I appreciated the authors desire & dream to biuld intelligent machines, he certainly lays down a probable theoretical approach. But the practical approach is just out of the question (at least that's what I think).
We will need 3-D electronic circuits to accomplish it, & that's just the tip of the ice-berg. To support such a complex 3-D architecture would reqiure an even more complex "information-filing" system (software).
It's true that intelligence biulds on itself, & the author claims we don't need a software, but that's because our brains have different cells for managing "information-filing" data. Whereas, electronic circuits don't, & the only way for it to organize data is through software.
Overall, I liked the book & it made me a former believer that "smart machines cannot build machines that are smarter".
Understanding intelligence - By: Coert Visser, 10 Dec 2004 We often routinely talk about intelligence & we attempt to measure it for for a variety of purposes. But do we know what it is? Jeff Hawkins is one of the first people to present a specific & comprehesensive theory of intelligence with a leading role for the human neocortex. Hawkins starts by stating that Human intelliigence is fundamentally different from what a computer does.
But isn't artifical intelligence (AI) a good metaphor for human intelligence? No, says Hawkins. In AI a computer is taught to solve problems beloning to a specific domain based on a large set of data & rules. In comparison to human intelligence AI systems are very limited. They are only good for the one thing they were designed for. Teaching an AI based system to perform a task like catching a ball is hard because it would require vast amounts of data & complicated algorithms to capture the complex features of the environment. A human would have little difficultyin solving such everyday problems much easier & quicker.
Ok, but aren't neural networks then a good approximation of human intelligence? Although they are indeed an improvement to AI & have made possible some very practical tools they are still very different to human intelligence. Not only are human brains structurally much more complicated, there are clear functional differences too. For instance,in a neural network information flows only one direction whilein the human brain there is a constant flow of informationin two directions.
Well, isn't the brain then like a parallel computerin which billions of cells are concurrently computing? Is parallel computing what makes human so fastin solving complex problems like catching a ball? No, says the author. He explains that a human being can perform significant tasks within much less time than a second. Neurons are so slow thatin that fraction of a second they can only traverse a chain of 100 neurons long. Computers can do nothing usefulin so few steps. How can a human accomplish it?
All right, human intelligence is different from what our computers do. What then is it? I'll try to summarize Hawkin's theory.
The neocortex constantly receives sequences of patterns of information, which it stores by creating so-called invariant representations (memories independent of details). These representations allow you to handle variationsin the world automatically. For instance, you can still recognize your friends face although she is wearing a new hairstyle.
All memories are storedin the synaptic connections between neurons. Although there is a vast amount of information storedin the neocortex only a few things are atively remembered at one time. This is so because a system, called `autoassociative memory' takes care that only the particular part of the memory is activated which is relevant to the current situation (the patterns that are currently flowingin the brain). On the basis of these activated memory patterns predictions are made -without us being aware of it- about what will happen next. The incoming patterns are compared to & combined with the patterns provided by memory resultin your perception of a situation. So, what you perceive is not only based on what your eyes, ears, etc tell you. In fact, theses senses give you fuzzy & partial information. Only when combined with the activated patterns from your memory, you get a consistent perception.
The hierarchical structure of the neocortex plays an important rolein perception & learning. Low regionsin the structure of the neocortex make low-level predictions (about concreet information like color, time, tone, etc) about what they expect to encounter next, while higher-level regions make higher-level predictions (about more abstract things. Understanding something means that the neocortex' prediction fits with the new sensory input. Whenever neocortex patterns & sensory patterns conflict, there is confusion & your attention is drawn to this error. The error is then sent up to higher neocortex regions to check if the situation can be understood on a higher level. In other words: are there patterns to be found somewhere elsein the neocortex, which do fit to the current sensory input?
Learning roughly takes place as follows. During repetitive learning memories of the world first formin higher regions of the cortex but as your learn they are reformedin lower parts of the cortical hierarchy. So, well-learned patterns are represented lowin the cortex while new information is sent to higher parts. Slowly but surely the neocortex buildsin itself a representation of the world it encounters. Hawkins: "The real world's nested structure is mirrored by the nested structure of your cortex."
This model explains well the efficiency & great speed of the human brain while dealing with complex tasks of a familiar kind. The downside is that we are not seeing & hearing precisely what is happening. When someone is talking we by definition don't fully listen to what he says. Instead, we constantly predict what he will say next & as long as there seems to be a fit between prediction & incoming sensory information our attention remains rather low. Only when he will say something, which is actively conflicting with our prediction, we will pay attention.
The author takes his model one step further by saying that even the motor system is prediction driven. In other words, the human neocortex directs behavior to satisfy its predictions. Hawkins says that doing something is literally the start of how we do it. Remembering, predicting, perceiving & doing are all very intertwined.
I think this is a fascinating & stimulating book. Many questions about intelligence may remain unanswered but I believe this book to be a step forwardin our quest to understand intelligence. The author predicts we can soon build intelligencein computersystems by using the principles of the neocortex. He is optimistic about what will happen once we succeedin this. He (reasonably convincing) argues these systems will be useful for humanity & not a threat.
Coert Visser, www.m-cc.nl
