In Jeff Hawkins’ MIT talk, he describes a theory that sensory regions of the neocortex process two inputs. One input is the well-known sensory data, and he proposes that the other is a representation of allocentric location. He discusses material from our March 2016 neuron paper and our October 2017 columns paper.
In this ODSC West talk, Matt Taylor discusses the biological path toward strong AI and why today’s AI won’t lead to truly intelligent machines. ODSC is a data science conference that fosters the exchange of the latest advances in AI and data science and encourages the growth of open source applications.
This video accompanies the paper titled “A Theory of How Columns in the Neocortex Enable Learning the Structure of the World” by Jeff Hawkins, Subutai Ahmad, and Yuwei Cui.
At Strange Loop, Numenta’s Matt Taylor gives a talk titled The Biological Path Toward Strong AI where he discusses details about our HTM technology, such as SDRs, Spatial Pooling, Temporal Memory, and Sensorimotor Inference.
HTM Chat with Jeff Hawkins is a video series in which our Open Source Community Manager, Matt Taylor, interviews Jeff Hawkins about a variety of HTM topics. Matt asks Jeff to talk about sensorimotor inference and seven other areas of interest to the HTM community.