Numenta is on a mission to solve the grand scientific challenge of figuring out how the brain works. Through a focus on cortical theory, Numenta researchers have made some important discoveries that lay the foundation for a new framework for intelligence. This video explains two of those discoveries, both documented in peer-reviewed papers.
In this talk in an AI Singapore Meetup on HTM, Matt Taylor discusses why today’s weak AI will not produce intelligence. He talks about details of our Hierarchical Temporal Memory (HTM) technology, such as Sparse Distributed Representations (SDRs), Spatial Pooling, Temporal Memory, and Sensorimotor Inference Theory.
Jeff Hawkins’ Simons Institute talk is part of the Computational Theories of the Brain Workshop held on April 17, 2018. In his talk, he proposes that the neocortex learns models of objects using the same methods that the entorhinal cortex uses to map environments.
Understanding the brain is one of science’s most important problems, and while many people believe it’s not solvable, researchers at Numenta disagree. Numenta is on a mission to reverse-engineer the brain and establish a path to machine intelligence. Watch this two minute video to see why the brain is not only a remarkable organ but the key to understanding intelligence.
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.