MSTDP: A More Biologically Plausible Learning

TL;DR

This paper introduces MSTDP, a biologically plausible learning framework based solely on STDP rules, capable of supervised and unsupervised tasks without global loss functions, demonstrated on MNIST for classification and generation.

Contribution

Proposes MSTDP, a novel STDP-based learning framework that mimics biological learning, eliminating the need for global supervision and enabling both classification and generation.

Findings

Effective on MNIST for classification

Able to generate patterns without extra modules

Uses iterative momentum-based inference

Abstract

Spike-timing dependent plasticity (STDP) which observed in the brain has proven to be important in biological learning. On the other hand, artificial neural networks use a different way to learn, such as Back-Propagation or Contrastive Hebbian Learning. In this work, we propose a new framework called mstdp that learn almost the same way biological learning use, it only uses STDP rules for supervised and unsupervised learning and don' t need a global loss or other supervise information. The framework works like an auto-encoder by making each input neuron also an output neuron. It can make predictions or generate patterns in one model without additional configuration. We also brought a new iterative inference method using momentum to make the framework more efficient, which can be used in training and testing phases. Finally, we verified our framework on MNIST dataset for classification and generation task.