More From Jeff Hawkins on Hierarchical Temporal Memory

Our few successes at building "intelligent" machines are notable equally for what they can and cannot do. Computers, at long last, can play winning chess. But the program that can beat the world champion can't talk about chess, let alone learn backgammon. Today's programs-at best-solve specific problems. Where humans have broad and flexible capabilities, computers do not.

....My colleagues and I have been pursuing that approach for several years. We've focused on the brain's neocortex, and we have made significant progress in understanding how it works. We call our theory, for reasons that I will explain shortly, Hierarchical Temporal Memory, or HTM. We have created a software platform that allows anyone to build HTMs for experimentation and deployment. You don't program an HTM as you would a computer; rather you configure it with software tools, then train it by exposing it to sensory data. HTMs thus learn in much the same way that children do. HTM is a rich theoretical framework that would be impossible to describe fully in a short article such as this, so I will give only a high level overview of the theory and technology.

...We have concentrated our research on the neocortex, because it is responsible for almost all high-level thought and perception, a role that explains its exceptionally large size in humans-about 60 percent of brain volume [see illustration "Goldenrod"]. The neocortex is a thin sheet of cells, folded to form the convolutions that have become a visual synonym for the brain itself. Although individual parts of the sheet handle problems as different as vision, hearing, language, music, and motor control, the neocortical sheet itself is remarkably uniform. Most parts look nearly identical at the macroscopic and microscopic level.

....Although the entire neocortex is fairly uniform, it is divided into dozens of areas that do different things. Some areas, for instance, are responsible for language, others for music, and still others for vision. They are connected by bundles of nerve fibers. If you make a map of the connections, you find that they trace a hierarchical design. The senses feed input directly to some regions, which feed information to other regions, which in turn send information to other regions. Information also flows down the hierarchy, but because the up and down pathways are distinct, the hierarchical arrangement remains clear and is well documented.

....Hierarchical representations solve many problems that have plagued AI and neural networks. Often systems fail because they cannot handle large, complex problems. Either it takes too long to train a system or it takes too much memory. A hierarchy, on the other hand, allows us to "reuse" knowledge and thus make do with less training. As an HTM is trained, the low-level nodes learn first. Representations in high-level nodes then share what was previously learned in low-level nodes.

....Because HTMs, like humans, can recognize spatial patterns such as a static picture, you might think that time is not essential. Not so. Strange though it may seem, we cannot learn to recognize pictures without first training on moving images. You can see why in your own behavior. When you are confronted with a new and confusing object, you pick it up and move it about in front of your eyes. You look at it from different directions and top and bottom. As the object moves and the patterns on your retina change, your brain assumes that the unknown object is not changing. Nodes in an HTM assemble differing input patterns together under the assumption that two patterns that repeatedly occur close in time are likely to share a common cause. Time is the teacher.

....The mapping between HTM and the detailed anatomy of the neocortex is deep. As far as we know, no other model comes close to HTM's level of biological accuracy. The mapping is so good that we still look to neuroanatomy and physiology for direction whenever we encounter a theoretical or technical problem.

Much more at IEEE Spectrum

Hat tip Impact Lab

Chess playing computers may be able to defeat Garry Kasparov, but you did not see any computers marching against the Putin mafiocracy in Moscow. High level chess playing computers only play chess. Even your five year old child would defeat a chess playing computer at Monopoly. Jeff Hawkins is trying to imbue machines with a more generalised intelligence than conventional digital computers can achieve.

Even so, it will be necessary to build the intelligence into the machine architecture, rather than programming it into a conventional machine. It will actually be the capacity for intelligence that must be built into the architecture.