Using brain inspired principles to unsupervisedly learn good representations for visual pattern recognition

TL;DR

This paper explores brain-inspired principles to develop unsupervised learning methods for visual pattern recognition, demonstrating competitive results on MNIST without relying on labeled data or back-propagation.

Contribution

It introduces a biologically inspired approach for unsupervised representation learning, diverging from traditional deep learning methods that depend on labeled data and back-propagation.

Findings

Achieved competitive classification accuracy on MNIST

Demonstrated effectiveness of brain-inspired unsupervised learning principles

Showed potential for biologically plausible models in visual recognition

Abstract

Although deep learning has solved difficult problems in visual pattern recognition, it is mostly successful in tasks where there are lots of labeled training data available. Furthermore, the global back-propagation based training rule and the amount of employed layers represents a departure from biological inspiration. The brain is able to perform most of these tasks in a very general way from limited to no labeled data. For these reasons it is still a key research question to look into computational principles in the brain that can help guide models to unsupervisedly learn good representations which can then be used to perform tasks like classification. In this work we explore some of these principles to generate such representations for the MNIST data set. We compare the obtained results with similar recent works and verify extremely competitive results.