Friday, September 14, 2007

Neural Networks vs. HTMs: What does Jeff Hawkins think?

Published by Evan Ratliff on Wired.com

Neural networks rose to prominence in the 1980s. But despite some successes in pattern recognition, they never scaled to more complex problems. Hawkins argues that such networks have traditionally lacked “neuro-realism”: Although they use the basic principle of inter-connected neurons, they don’t employ the information-processing hierarchy used by the cortex. Whereas HTMs continually pass information up and down a hierarchy, from large collections of nodes at the bottom to a few at the top and back down again, neural networks typically send information through their layers of nodes in one direction — and if they send information in both directions, it’s often just to train the system. In other words, while HTMs attempt to mimic the way the brain learns — for instance, by recognizing that the common elements of a car occur together — neural networks use static input, which prevents prediction. Click for more...

No comments: