Tuesday, June 23, 2009

Theories of the Brain

As a summary, what Jeff Hawkins says on page 2 of On Intelligence seems accurate to me and note this was published in 2004:
Yet we have no productive theories about what intelligence is or how the brain works as a whole. Most neurobiologists don't think much about overall theories of the brain because they're engrossed in doing experiments to collect more data about the brain's many subsystems. And although legions of computer programmers have tried to make computers intelligent, they have failed. I believe they will continue to fail as long as they keep ignoring the differences between computers and brains.
Of course later Hawkins discusses in some detail both neuroscience and attempts at creating human-like machine behavior with what we will call the old AI, or Artificial Intelligence.

All of my experience led me to the same conclusion. It is not that some scientists, computer software engineers, and philosophers have not looked at the problems that On Intelligence addresses. In retrospect, however, most of them made the same fundamental mistake. Characterize it as trying to replicate behavior instead of creating intelligence that replicates human intelligence and therefore human behavior. And one reason most people made the same mistake was because there was no good model of the brain available from the neuroscientists.

I have on my bookshelf The Formal Mechanics of Mind by Stephen N. Thomas. The inside cover blurb says "The author's intention is to provide an analysis of the nature of the mind, and of our knowledge of it—an analysis that solves or avoids longstanding philosophical problems and that fits well with the results of psychological and neuropsychological investigations of mental phenomena." It is a good book. Published in 1978, it is one of the best I had read before On Intelligence.

On the other hand we have the computer programming AI people. They did some pretty good work, but it is a cautionary tale. Most AI worked with very simple models of objects. AI did best, or appeared to do best, when dealing with certain higher human mental functions, like formal logic. But the brain does not appear to operate with formal logic. Humans invented formal logic. It may (or may not) serve as a basis for a theory of mathematics, as Bertrand Russel, A. N. Whitehead, Ludwig Wittgenstein, and John von Neuman attempted to show.

We will, of course, be using mathematics to understand "real" intelligence. Yet there is almost no math in On Intelligence. Before we can develop a math, or apply an existing branch of mathematics, to this problem we have to understand both the true nature of the problem and how the brain implements the solution, both structurally and dynamically.

I also have on my bookshelf, among other books on neural networks, Parallel Distributed Processing by James L. McClelland et. al. I wrote some computer programs to implement some of the models presented in the book. That was back in the late 1980's. The intelligence problem, then, seemed to be solvable in a piecemeal manner. Difference types of neural networks could be combined and improved until something approaching intelligence emerged. But my own attempts at building an intelligence model went nowhere, and I got involved in trying to save some redwood forests. The forests were clearcut despite my efforts, and I'll take Hawkins' word for it when he said that the neural network model had not made substantial progress in the 1990's. Again, neural network software and hardware became very good at certain things, notably pattern recognition. But while intelligent systems (humans) can recognize patters, apparently pattern recognition is not in itself the basis of intelligence.

Next up: Real Intelligence versus AI

No comments:

Post a Comment