On Intelligence by Jeff Hawkins
Posted on June 5th, 2005
This book is great. Before reading it I had never gave the brain much thought when I was reading about the techniques of creating intelligent machines. The focus always seemed to be about reaching the finishing line rather than the exact route taken-- if there's an algorithm or set of algorithms that can achieve something that looks and acts like intelligence, similarity to how the human brain works isn't all that critical.
Hawkins suggests that the it's not so much the computational speed or the memory or the reliability of computers that need improvement (although more is of course better), it's their ability to process input the way the brain does. We filter irrelevant input from important input all the time, but the way the brain carries out that filtering doesn't quite have a machine equivalent. Computers don't recognize patterns nearly as well as the brain can. And this is a main point of On Intelligence: the human brain is a great big pattern matching engine.
The matching engine idea makes a lot of sense to me, in part because PubSub uses the same idea to describe its ability to bring you content relevant to whatever subject you're interested in.
p. 59
We teach our children that humans have five senses: sight, hearing, touch, smell, and taste. We really have more. Vision is more like three senses-- motion, color, and luminance (black-and-white contract). Touch has pressure, temperature, pain, and vibration. We also have an entire system of sensors that tell us about our joint angles and body position. It is called the proprioceptive system (proprio- has the same Latin root as proprietary and property). You couldn't move without it. We also have the vestibular system in the inner ear, which gives us our sense of balance. Some of these senses are richer and more apparent to use than others, but they all enter our brain as streams of spatial patterns flowing through time on axons.
Your cortex doesn't really know or sense the world directly. The only thing the cortex knows is the pattern streaming in on the input axons. Your perceived view of the world is created from these patterns, including your sense of self. In fact, your brain can't directly know where your body ends and the world begins.
p. 62
Brains are pattern machines. It's not incorrect to express the brain's functions in terms of hearing or vision, but at the most fundamental level, patterns are the name of the game. No matter how different the activities of various cortical area may seem from each other, the same basic cortical algorithm is at work. The cortex doesn't care if the patterns originated in vision, hearing, or another sense. It doesn't care if its inputs are from a single sensory organ or from four. Nor would it care if you happened to perceive the world with sonar, radar, or magnetic fields, or if you had tentacles rather than hands, or even if you lived in a world of four dimensions rather than three.
This means you don't need any one of your senses or any particular combination of senses to be intelligent.
p. 73
There are thousands of detailed memories stored in the synapses of our brains that are rarely used. At any point in time we recall only a tiny fraction of what we know. Most of the information is sitting there idly waiting for the appropriate cues to invoke it.
p. 75
Thoughts and memories are associatively linked, and and again, random thoughts never really occur. Inputs to the brain auto-associatively link to themselves, filling in the present, and auto-associatively link to what normally follows next. We call this chain of memories thought, and although its path is not deterministic, we are not fully in control of it either.
p. 82
Memories are stored in a form that captures the essence of relationships, not the details of the moment. When you see, feel, or hear something, the cortex takes the detailed, highly specific input and converts it to an invariant form. It is the invariant form that is stored in memory, and it is the invariant form of each new input pattern that it gets compared to. Memory storage, memory recall, and memory recognition occur at the level of invariant forms. There is no equivalent concept in computers.
p. 104
The human cortex is particularly large and therefore has a massive memory capacity. It is constantly predicting what you will see, hear, and feel, mostly in ways you are unconscious of. These predictions are our thoughts, and, when combined with sensory input, they are our perceptions. I call this view of the brain the memory-prediction framework of intelligence
p. 171
We could say the more you know, the less you remember.
p. 172
You normally don't perceive the individual letters while reading; you perceive words or phrases. But you can perceive the letters if you choose to. We are doing this sort of attentional shift all the time, but we aren't generally aware of it. I can be listening to music playing in the background and barely be aware of the melody, but if I try, I can isolate the singer or the bass guitar. The same sound is entering my head, but I can focus my perceptions. Every time you scratch your head, the movement makes a loud internal sound, but usually you are unaware of the noise. If you focus on it, though, you can hear the sound clearly. This is another example of sensory input that normally is handled low in the cortical hierarchy but can be brought to higher levels if you attend to it.
p. 185
Prediction by analogy-- creativity-- is so pervasive we normally don't notice it. We do, however, believe we are being creative when your memory-prediction system operates at a higher level of abstraction, when it makes uncommon predictions, using uncommon analogies.
p. 187
Creativity is mixing and matching patterns of everything you've ever experienced or come to know in your lifetime. It's saying "this is kinda like that." The neural mechanism for doing this is everywhere in the cortex.
p. 188
An expert is someone who through practice and repeated exposure can recognize patterns that are more subtle than can be recognized by a non-expert, such as the shape of a fin on a late-fifties car or the size of a spot on a seagull's beak. Experts can recognize patterns on top of patterns. Ultimately there is a physical limit to what we can learn constrained by the size of our cortex. But as humans, our cortex is large compared to other species and we have a tremendous flexibility in what we can learn. It all depends on what we are exposed to throughout our lives.
p. 192
Our brains prefer systems that are consistent and predictable, and we like learning new skills.
p. 199
To the cortex, our bodies are just part of the external world. Remember, the brain is in a quiet and dark box. It knows about the world only via the patterns on the sensory nerve fibers. From the brain's perspective as a pattern device, it doesn't know about your body any differently than it knows about the rest of the world. There isn't a special distinction between where the body ends and the rest of the world begins. But the cortex has no ability to model the brain itself because there are no sense in the brain. Thus we can see why our thoughts appear independent of our bodies, why it feels like we have an independent mind or soul. The cortex builds a model of your body but it can't build a model of the brain itself. Your thoughts, which are located in the brain, are physically separate from the body and the rest of the world. Mind is independent of body, but not of brain.