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

2020/05/06 by Ravichandran, Naresh Balaji, Lansner, Anders, Herman, Pawel · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)

paper · doi:10.48550/arxiv.2005.03476

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.

Cited by

• Embedded FPGA Acceleration of Brain-Like Neural Networks: Online Learning to Scalable Inference

Related

• Semi-supervised learning with Bayesian Confidence Propagation Neural\n Network
• Unsupervised representation learning with Hebbian synaptic and structural plasticity in brain-like feedforward neural networks
• Learning Deep Representation Without Parameter Inference for Nonlinear Dimensionality Reduction
• Spiking neural networks with Hebbian plasticity for unsupervised representation learning
• Parsimonious Bayesian deep networks