On Intelligence: How a New Understanding of the Brain Will Lead to the Creation of Truly Intelligent Machines

by Jeff Hawkins

I believe the best way to solve this problem is to use the detailed biology of the brain as a constraint and as a guide, yet think about intelligence as a computational problem—a position somewhere between biology and computer science.

AI scientists tried to program computers to act like humans without first answering what intelligence is and what it means to understand.

Complexity is a symptom of confusion, not a cause.

Some people fear that intelligent machines could be dangerous to humanity, but I argue strongly against this idea.

It will be far easier to build machines that outstrip our abilities in high-level thought such as physics and mathematics than to build anything like the walking, talking robots we see in popular fiction.

Some of the details of what I propose are certain to be wrong, which is always the case in any area of science.

The mathematician Paul Erdös believed that the simplest mathematical proofs already exist in some ethereal book and a mathematician’s job was to find them, to “read the book.”

computers. The idea was that neurons could act as what engineers call logic gates.

Deep Blue didn’t win by being smarter than a human; it won by being millions of times faster than a human.

According to functionalism, being intelligent or having a mind is purely a property of organization and has nothing inherently to do with what you’re organized out of.

But information in the cortex always flows in the opposite direction as well, and with many more projections feeding back down the hierarchy than up.

It followed naturally from a single observation: that the speed of light is constant to all observers even if the observers are moving at different speeds.

He proposes that the cortex uses the same computational tool to accomplish everything it does.

Therefore, Mountcastle argues, all regions of the cortex are performing the same operation.

Written language is far too recent an invention for our genes to have evolved a specific mechanism for it.

It matters where the cables go to inside the brain.

Your perceptions and knowledge about the world are built from these patterns. There’s no light inside your head. It’s dark in there. There’s no sound entering your brain either. It’s quiet inside. In fact, the brain is the only part of your body that has no senses itself.

Spatial patterns are coincident patterns in time; they are created when multiple receptors in the same sense organ are stimulated simultaneously.

For example, if I give you a little rake and have you use it for reaching and grasping instead of using your hand, you will soon feel that it has become a part of your body. Your brain will change its expectations to accommodate the new patterns of tactile input. The rake is literally incorporated into your body map.

These examples show once again that the cortex is extremely flexible and that the inputs to the brain are just patterns. It doesn’t matter where the patterns come from; as long as they correlate over time in consistent ways, the brain can make sense of them.

a system running the neocortical algorithm will be intelligent based on whatever kinds of patterns we choose to give it.

The senses create patterns that are sent to the cortex, and processed by the same cortical algorithm to create a model of the world. In this way, spoken language and written language are perceived remarkably similarly, despite being completely different at the sensory level. Likewise, Helen Keller’s model of the world was very close to yours and mine, despite the fact that she had a greatly reduced set of senses. Through these patterns the cortex constructs a model of the world that is close to the real thing, and then, remarkably, holds it in memory.

The entire cortex is a memory system. It isn’t a computer at all.

The memory of how to catch a ball was not programmed into your brain; it was learned over years of repetitive practice, and it is stored, not calculated, in your neurons.

Truly random thoughts don’t exist. Memory recall almost always follows a pathway of association.

An auto-associative memory system is one that can recall complete patterns when given only partial or distorted inputs.

For the most part we are not aware that we’re constantly completing patterns, but it’s a ubiquitous and fundamental feature of how memories are stored in the cortex. At any time, a piece can activate the whole. This is the essence of auto-associative memories.

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.

We don’t remember or recall things with complete fidelity—not because the cortex and its neurons are sloppy or error-prone but because the brain remembers the important relationships in the world, independent of the details.

What we perceive is a combination of what we sense and of our brains’ memory-derived predictions.

Rather, the job of any cortical region is to find out how its inputs are related, to memorize the sequence of correlations between them, and to use this memory to predict how the inputs will behave in the future.

If the patterns are related in such a way that the region can learn to predict what pattern will occur next, the cortical region forms a persistent representation, or memory, for the sequence.

As strange as it sounds, when your own behavior is involved, your predictions not only precede sensation, they determine sensation.

I speculate that the alternate pathway through the thalamus is the mechanism by which we attend to details that normally we wouldn’t notice.

Neurons probably evolved as a way to communicate information more quickly than a plant’s vascular system.

At some point, instead of slowly moving chemicals along these appendages, the neuron started using electrochemical spikes, which travel much faster.

Our most contemplative thoughts are not driven by or even connected to the real world; they are purely a creation of our model.

consequences. If my theory of intelligence is right, we cannot rid people of their propensity to think in stereotypes, because stereotypes are how the cortex works.

There is a saying in the high-tech world that change takes longer than you expect in the short term but occurs faster than you expect in the long term.