There’s a good article on Read/WriteWeb about Numenta, a layered approach to artificial intelligence called Hierarchical Temporal Memory. From the article:
Similar to the neural networks, HTM does not have any prewired classification of the world. Instead, HTM accepts a sequence of spacio-temporal inputs and ‘learns’ the patterns in the input stream. In the diagram above, the senses digitize the signal and turn them into bitmaps (or vectors), which are then are processed by a classification system. The system then assigns the likelihood of a particular cause to each symbol. In plain english, you are shown a sequence of pictures of cats and dogs - and each picture you classify as either a cat or a dog. But just like we can’t do that when we are born, neither can HTM. In fact HTM needs to go through a training process before it can ‘learn’ to distinguish things.
Here’s the full post on Numenta. The company has also made available some Hierarchical Temporal Memory whitepapers as well as their source code (which I have yet do download myself).