# Unsupervised Learning via Total Correlation Explanation

## TL;DR

The paper introduces the CorEx principle, an unsupervised learning approach that explains data dependence using total correlation, demonstrating success across various domains such as behavior, biology, and language.

## Contribution

It proposes a novel unsupervised learning framework based on total correlation explanation, unifying and advancing dependence-based representation learning.

## Key findings

- Effective in modeling dependence in sensory data
- Applied successfully across multiple domains
- Provides a theoretical foundation for unsupervised learning

## Abstract

Learning by children and animals occurs effortlessly and largely without obvious supervision. Successes in automating supervised learning have not translated to the more ambiguous realm of unsupervised learning where goals and labels are not provided. Barlow (1961) suggested that the signal that brains leverage for unsupervised learning is dependence, or redundancy, in the sensory environment. Dependence can be characterized using the information-theoretic multivariate mutual information measure called total correlation. The principle of Total Cor-relation Ex-planation (CorEx) is to learn representations of data that "explain" as much dependence in the data as possible. We review some manifestations of this principle along with successes in unsupervised learning problems across diverse domains including human behavior, biology, and language.