Computing Like the Brain
The neocortex works on principles that are fundamentally different than traditional computers. In this talk I will describe recent advances in understanding these principles and their impact on future computer architectures. The talk will start with a description of sparse distributed representations, which are the fundamental units of information in brains. I will then discuss how these representations are learned and how the brain processes them to build predictive models from high velocity sensory data streams. Numenta has built a streaming analytics engine based on these principles. I will give a brief introduction to this product and speculate on the future of machine intelligence.
Jeff Hawkins is a co-founder of Numenta. Numenta is creating a new computing platform designed on the principles of the neocortex. Previous to Numenta he founded the Redwood Neuroscience Institute and two mobile computing companies, Palm and Handspring, where he was the architect of computing products such as the PalmPilot and Treo smartphone. In 2004 he wrote the book “On Intelligence” which describes progress in understanding the neocortex.
Jeff Hawkins earned his B.S. in electrical engineering from Cornell University in 1979. He was elected to the National Academy of Engineering in 2003.