The Thousand Brains Theory of Intelligence and its Implications for AI

Jeff Hawkins and Subutai Ahmad

Numenta, Inc.
Wednesday, April 21, 2021 at 12:00pm

The neocortex exhibits a detailed architecture that is largely preserved across different functional areas and between species. This has led to the idea of a common cortical algorithm that underlies all aspects of perception, language, and thought. Whether such a common algorithm exists and what it could be has been debated for decades. Our team has proposed an answer to these questions, which we call the Thousand Brains Theory of Intelligence. We propose that the overall goal of the neocortex is to learn a model of the world. The model is distributed in that every cortical column is a complete sensory-motor modeling system. Columns learn by assigning sensory data to locations in reference frames, directly related to how grid cells and place cells learn models of environments. Knowledge of any particular object, such as a coffee cup, is distributed among thousands of columnar models in different sensory modalities. The columns use a voting mechanism to reach a consensus of what they are observing. In this talk, we will give an overview of The Thousand Brains Theory of Intelligence, discuss recent empirical observations that support the theory, discuss how our findings can improve existing artificial neural networks, and create a roadmap for new AI architectures. Hawkins also has a new book titled, A Thousand Brains, A New Theory of Intelligence that describes the theory and its implications.


Jeff Hawkins, a neuroscientist and technologist, is the co-founder of Numenta, a neuroscience research company; founder of the Redwood Neuroscience Institute (now the Redwood Center for Theoretical Neuroscience at U.C. Berkeley); and one of the founders of the field of handheld computing. He is a member of the National Academy of Engineering and author of On Intelligence and A Thousand Brains, A New Theory of Intelligence.

Subutai Ahmad, PhD, is the VP of Research at Numenta, with experience in computational neuroscience, deep learning, and computer vision. His research interests are focused on creating a detailed theory of the neocortex, and applying its concepts to machine learning.