Most famous for his work with Palm where he took part in creating the first handheld computers, Jeff Hawkins has recently got himself into neuroscience.
In a TEDTalks video urges us to take a new look at the brain — to see it not as a fast processor, but as a memory system that stores and plays back experiences to help us predict, intelligently, what will happen next.
- Why we don’t have a good brain theory.
- What it’s important.
- What we can do about it.
Hawkins argues that what’s lacking is a theoretical framework. We have lots of data, but little in the way of theory. This is where Hawkins seeks to contribute, most famously with his hierarchical temporal model of memory. Memoirs of a Postgrad has a far better summary of the theory here. The theory is that the brain is basically a big memory system that uses past experiences to make predictions about the future – this is Hawkins’ definition of intelligence. So in this view, we literally learn from experience.
Coaxing computers to perform basic acts of perception and robotics, let alone high-level thought, has been difficult. No existing computer can recognize pictures, understand language, or navigate through a cluttered room with anywhere near the facility of a child. Hawkins and his colleagues have developed a model of how the neocortex performs these and other tasks.
The theory, call Hierarchical Temporal Memory, explains how the hierarchical structure of the neocortex builds a model of its world and uses this model for inference and prediction. To turn this theory into a useful technology, Hawkins has created a company called Numenta. Hawkins describes the theory, its biological basis, and a software platform created by Numenta that allows anyone to apply this theory to a variety of problems. Part of this theory was described in a book he co-authored in 2004 called “On Intelligence”.