English

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

Neural and Evolutionary Computing 2021-04-19 v2 Machine Learning

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 usefulness and class-dependent separability of the hidden representations when trained on MNIST and Fashion-MNIST datasets is studied using an external linear classifier and compared with other unsupervised learning methods that include restricted Boltzmann machines and autoencoders.

Keywords

Cite

@article{arxiv.2005.03476,
  title  = {Brain-like approaches to unsupervised learning of hidden representations -- a comparative study},
  author = {Naresh Balaji Ravichandran and Anders Lansner and Pawel Herman},
  journal= {arXiv preprint arXiv:2005.03476},
  year   = {2021}
}

Comments

arXiv admin note: text overlap with arXiv:2003.12415

R2 v1 2026-06-23T15:22:57.785Z