Unsupervised Learning through Prediction in a Model of Cortex
This work addresses foundational challenges in computational neuroscience for understanding brain-like learning, but it appears incremental as it builds directly on Valiant's existing model.
The paper tackles the problem of unsupervised learning in cortical models by proposing a primitive called PJOIN that extends Valiant's computational theory, showing it can implement memory-based prediction and downward traffic in cortical hierarchies for complex learning tasks.
We propose a primitive called PJOIN, for "predictive join," which combines and extends the operations JOIN and LINK, which Valiant proposed as the basis of a computational theory of cortex. We show that PJOIN can be implemented in Valiant's model. We also show that, using PJOIN, certain reasonably complex learning and pattern matching tasks can be performed, in a way that involves phenomena which have been observed in cognition and the brain, namely memory-based prediction and downward traffic in the cortical hierarchy.