Evaluating HTMs, Part 2: What HTMs Do

For the introduction See Evaluating HTMs, Part 1

"Hierarchical Temporary Memory, Concepts, Theory, and Terminology " by Hawkins and George, Section 1, What Do HTMs Do?, asserts that HTMs can discover causal relationships in data presented to them. Once the causality is established, they can infer the cause of a new input. They can predict (with some accuracy) future data sets, and they can use the above three abilities to direct (choose) behavior.

It should be pointed out immediately that each of these 4 abilities have been demonstrated by other computational systems. Neural network software that could discover certain types of relationships from raw data was available at least as early as the 1980's. Many mathematical forms of analysis can find causal relationships within data, for instance regression analysis. In any system, once a relationship is established, recognizing it should present no great difficulty. Nor should making predictions, or using the system to control behavior.

What is interesting about the set of claims for HTMs is that they work together holistically (like the human brain) and should be stackable. That is, the HTM systems should be able to deal with external relationships of increasing complexity by stacking HTM subsystems into an appropriate system. In addition, the HTMs can find relationships in time (sequential or temporal relationships).

In fact, if we call some of the data "objects," for an HTM the objects "have a persistent structure; they exist over time." The authors call the objects "causes." In theory an HTM system could deal with multiple forms of data coming in directly from the world, but usually (for now) the HTM deals with a specific subset of data (much as when a human, say, concentrates on music, or on reading). The data could be a computer file, or a stream of data from input devices.

For the HTM to work the causes should be relatively stable, but should generate data that changes over time, as a horse moving across a visual field, or a conversation between two people. Causes are typically multiple.

The discovery of the causal relationships is a learning process. During learning the HTM builds representations of causes in the form of vectors. The relationship is expressed as a set of probabilities for causes; this set is called a "belief." The causes, relationships, and beliefs can be quite complex if the HTM is complex enough. In particular, hierarchies of causes and beliefs can be learned.

The authors say an HTM, once it has gone through learning, can "infer causes of a novel input." This means that if it is presented with new data, it will try to match the data up to one of the causes it knows about. This is basically pattern recognition, and there are other systems, including certain neural networks, that do this well in certain situations. A good point made by is that if a million pixel visual field (of a scene with motion) is used as the input, it would be rare that an exact pattern would be input twice. So inference, matching a set of data to the closest cause, is a necessity. In the older neural networks causes were typically static; adding a time dimension to the data usually makes it easier for an HTM to learn and infer. I should point out, however, that "infer causes of novel input," to me can mean something more than is claimed by an HTM. For humans, it can mean a deduction, or even a deep set of deductions, rather than just recognizing a pattern or its degree of ambiguity. Then again, perhaps a sufficiently complete HTM system could do even that.

The ability to predict is the third leg of what HTMs do. In other words, given a sequence already encountered, an HTM will predict that sequence is happening again. This sounds like not much, but it is an ability that is crucial to machine understanding. In particular the authors point to priming. Given the latest data, the HTM makes a prediction and notes differences between what is predicted and what happens. If data is ambiguous or noisy, the HTM may fill in with the predicted data. If a prediction is fed back into the HTM as data, this is akin to thinking or imagining. Thus the machine could plan for the future. The authors claim "HTMs can do this well." Imagine a sheep-herding dog application. The better it can predict the behavior of the sheep, the less energy it should need to herd them.

Finally, HTMs can direct behavior. Of course almost any device, even simple mechanical ones, can direct behavior. A mouse trap, given a certain type of input, will engage in a known set behavior. Still, mentioning this for HTMs is important because that is exactly what we would expect artificial intelligence or machine understanding to be used for: behavior. An important point is that "From the HTM's perspective, the [output] system it is connected to is just another object in the world." In other words, an HTM can learn about how its own outputs act is causes in the world.

If you want to get an idea of the potential power of HTMs, before wading through a lot of other materials, section 1.4 of the paper "Direct Behavior", is a great starting point.

I'm excited after reading this part.

Possible Acronym: LIPD (learn, infer, predict, direct)

Next: How do HTMs discover and infer causes?

The Cortex, Dogs, and Changes of Coordinates

I finished my second read-though of On Intelligence by Jeff Hawkins several weeks ago. I got a lot out of this reading, and even was able to follow the details of Chapter 6 which eluded me the first time. Despite good intentions I neglected to write down my much-provoked thoughts until now. I have been spending most of that time indexing the new edition of Windows Internals by Mark Russinovich et. al., which is interesting in an entirely different way: one sees the products of human intelligence, but it is obvious that there is no danger of a Windows operating system of the current style becoming intelligent or conscious, ever.

In addition to following Jeff's suggestions about noticing how my own mind works, I have been thinking about these matters while watching my dog, Hugo. Let's say he represents mammals in general. He may not have the big old cortex that Jeff admires so much, but he seems to be constantly using his little one to make predictions. Hugo has to make a lot of decisions, and he often freezes in place while making them. Come when called? Maybe, maybe not. A treat in hand might just mean being captured and taken indoors, or left out of a car ride. To make such decisions, I believe, Hugo has to predict outcomes.

Like most dogs, Hugo likes to chase thrown toys. He has come to associate arm movements with probable outcomes. He knows if you are throwing in a particular direction, and begins his run in that direction without waiting for the toy to be released. He expects the toy to appear in front of him. If it does not, he looks back. Will I go ahead and throw the toy past him, or throw it in another direction.

Do this a few times, and he stops dashing as soon as my arm is moving. He waits to see if and where where I actually throw the toy.

I also believe Hugo has a construct of the world very similar to our human construct. He navigates the real world with an ease that can only come from having an internal map of the world. He understands the three-dimensional nature of the world, and in particular that obstacles like a tree or a house can have space behind them.

All this means is that if we want to build cortex like machine designs, we can do a lot without having to recreate a human brain. A car as smart as Hugo could go anywhere it wants on roads without smashing into other cars. This reminds me of science fiction stories where human brains are disembodied and plugged directly into space ships.

So maybe our first goal should be to create animal-brain equivalents and see what can be done with them.

I just happen to be reviewing the branch of mathematics that deals with changes of coordinates. I've always wanted to understand quantum physics and general relativity better, so I occasionally break open a math book, because at some point you must do the math to know what the smart guys are talking about. It is clear to me that human brains, and probably mammal brains too, are pretty good at changes of coordinates. The fact that we construct a mental map of the world and so easily map visual, audio, and tactile coordinates to it and back again is pretty remarkable.

I am again about to review how invariants are treated in tensor mathematics. Maybe that has nothing to do with the ability of the cortex to navigate the world, but it just might. Our brains certainly are good at creating invariant memories and comparing them to real world experiences.

Using the cortex to analyze the cortex: now that is a wonder.

Gambling, Addiction and Prediction

Why do people love to gamble? True, there is a range of how much various people like to gamble. At one end there are people are (or pretend to be) bored by it (I exclude people who, for whatever reason, won’t even try games of chance or skill). At the other end are people who lose their savings, homes, and families, or even fingers and lives to legal and illegal gambling operations.

It may all have to do with the brain’s built-in prediction mechanisms.

According to Jeff Hawkins’s theory of the sequential and predictive basis of human intelligence, the primary intelligent function of the brain is to remember sequences of data and use that memory to predict future sequences of data. This is true both for sensory data that we think of as naturally sequential, like the notes in a music tune, and for sensory data that we normally think of as non-sequential, like the features in a human face. According to the theory we construct a model of a human face from sequences of visual input (supplemented by other data, like touching one’s own face). If we see an eye, we expect to see a sequence of other features: another eye, a nose, mouth, eyebrows, hair, chin, ears. We expect to hear a voice when a mouth moves, but not when an eye blinks.

An important element in building a model of the world is surprise. Using memory, the brain predicts what it expects to see, hear, and feel next. When something different occurs, the element of surprise turns on higher functions in the brain. We may look at something more closely. Perhaps it is a face, but it is a strange face. Is this a sign of danger? Friend or foe, we need to memorize the new face and whatever we associate with it (perhaps the face belongs to someone who is being introduced by a friend; we need to remember that association, or the physical place where we met the person).

There is a bit of a nervous rush when a prediction is made that turns out to be false. The mind gears up to determine why it made a false prediction, both in order to deal with the unexpected situation and to be able to predict it in the future. Probably this rush is partly neurochemical. We’ll call it a bit of adrenaline, although it is possibly based on another neurotransmitter or hormone. Adrenaline rush is the lay term I will use.

Games can teach, and they can while the time away. Even when they are not played for money or prizes, they can have an addictive quality. In almost every game an element of prediction is involved. The outcome provides relief if it was predicted, and a rush of neural activity if it was not predicted.

Generally, people like adrenaline rushes, especially in small doses. They like a thrill more than they like boredom. Games are played partly because they provide small, safe levels of thrill in situations that would otherwise being predictable and boring.

Gambling involves making a prediction. It involves two highs for the human brain. Most of us enjoy winning. Getting money from winning gives the same motivation as getting a snack, affection, or a pay check.

I believe that it is losing, however, that makes gambling addictive. When you lose in a random game of chance, your brain is fooled. It made a prediction. It was surprised by the outcome. Now it is designed to frantically memorize what happened and construct a way of making a correct prediction.

Gamblers often come to believe, after a string of losses, that they are about to make a correct prediction or a series of correct predictions. This is how your brain works: long experience has taught it that nature is a set of sequences, and past sequences can predict future sequences. The brain is fooled by the artificial construction of random events like dice throws, roulette wheel spins, and card deals. Worse, there is a sometimes-confusing element of predictability to some of this (two dice will roll a seven more often than a two; in poker three of a kind comes up more often than four of a kind) that tends to reinforce the brains belief that it can make sense out of randomness. The brain persists in the false belief that random events become predictable if only you keep placing bets long enough.

There is a rush when losing. People, on a chemical level, don’t feel pain when they lose. The chips or money they gamble is abstract, removed from the necessities or pleasures they could buy if had not lost. But the loss forces the higher intelligence centers of the brain to gear up. It is like taking a tiny bit of a stimulant. It is pleasurable.

This is often why otherwise highly intelligent individuals will lose vast sums of money in casinos. It is precisely like drug addiction. They may, at some conscious level, when away from a casino, coldly say that they understand they cannot beat a random game with odds set so that the house wins. But in the casino they cannot get out of the loop of feeding themselves tiny bits of adrenaline with each wager, win or lose.