Unsupervised Learning via Total Correlation Explanation

Unsupervised Learning via Total Correlation Explanation

Greg Ver Steeg

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
Early Career. Pages 5151-5155. https://doi.org/10.24963/ijcai.2017/740

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.
Keywords:
Machine Learning: Unsupervised Learning
Multidisciplinary Topics and Applications: Multidisciplinary Topics and Applications
Machine Learning: Deep Learning
Machine Learning: Machine Learning