Brain-like approaches to unsupervised learning of hidden representations - a comparative study

Naresh Balaji, Anders Lansner, Pawel Herman

Keywords: neural networks, bio-inspired, brain-like, unsupervised learning, structural plasticity

Abstract: Unsupervised learning of hidden representations has been one of the most vibrant research directions in machine learning in recent years. In this work we study the brain-like Bayesian Confidence Propagating Neural Network (BCPNN) model, recently extended to extract sparse distributed high-dimensional representations. The saliency and separability of the hidden representations when trained on MNIST dataset is studied using an external linear classifier and compared with other unsupervised learning methods that include restricted Boltzmann machines and autoencoders.

One-sentence Summary: We compare unsupervised learning algorithms implementing biologically plausible local plasticity rules on MNIST dataset, with special emphasis on the Bayesian Confidence Propagating Neural Network (BCPNN).

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=oqlFCMYbiQ