Cortical Learning via Prediction
Abstract
What is the mechanism of learning in the brain? Despite breathtaking advances in neuroscience, and in machine learning, we do not seem close to an answer. Using Valiant’s neuronal model as a foundation, we introduce PJOIN (for “predictive join"), a primitive that combines association and prediction. We show that PJOIN can be implemented naturally in Valiant’s conservative, formal model of cortical computation. Using PJOIN — and almost nothing else — we give a simple algorithm for unsupervised learning of arbitrary ensembles of binary patterns (solving an open problem in Valiant’s work). This algorithm relies crucially on prediction, and entails significant downward traffic (“feedback") while parsing stimuli. Prediction and feedback are well-known features of neural cognition and, as far as we know, this is the first theoretical prediction of their essential role in learning.
Cite
Text
Papadimitriou and Vempala. "Cortical Learning via Prediction." Annual Conference on Computational Learning Theory, 2015.Markdown
[Papadimitriou and Vempala. "Cortical Learning via Prediction." Annual Conference on Computational Learning Theory, 2015.](https://mlanthology.org/colt/2015/papadimitriou2015colt-cortical/)BibTeX
@inproceedings{papadimitriou2015colt-cortical,
title = {{Cortical Learning via Prediction}},
author = {Papadimitriou, Christos H. and Vempala, Santosh S.},
booktitle = {Annual Conference on Computational Learning Theory},
year = {2015},
pages = {1402-1422},
url = {https://mlanthology.org/colt/2015/papadimitriou2015colt-cortical/}
}