Unsupervised Learning through Prediction in a Model of Cortex

2014/12/26 by Christos H. Papadimitriou, Santosh S. Vempala, Santosh Vempala +2 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · Mathematics · Neuroscience · #Data Structures and Algorithms (cs.DS) #EEG and Brain-Computer Interfaces #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (stat.ML) #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE) #Neural dynamics and brain function #Neurons and Cognition (q-bio.NC) #cs.DS #cs.NE #q-bio.NC #stat.ML

paper · pdf · doi:10.48550/arxiv.1412.7955

arxiv created 2014/12/26 · openalex publication_date 2014/12/26 · arxiv updated 2014/12/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Gradient-based learning applied to document recognition

Cited by

• Computational Tradeoffs in Biological Neural Networks: Self-Stabilizing Winner-Take-All Networks

Related

• Encoding Reality: Prediction-Assisted Cortical Learning Algorithm in Hierarchical Temporal Memory
• A neuro-inspired architecture for unsupervised continual learning based on online clustering and hierarchical predictive coding
• Constrained Predictive Coding as a Biologically Plausible Model of the Cortical Hierarchy
• Architecture of a Cortex Inspired Hierarchical Event Recaller
• Understanding neural circuit principles for representation learning through joint-embedding predictive architectures