A Theory of How Columns in the Neocortex Enable Learning the Structure of the World
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. It is published in the Frontiers in Neural Circuits journal.
It illustrates the inference mechanism described in the paper and introduces the theory of location information, showing how cortical columns can use location information to form robust predictive models of objects.
The video examines how a human recognizes objects just through touch by simulating a hand. Although the video uses touch, the same mechanism can be applied to all sensory modalities.