aSTDP: A More Biologically Plausible Learning

TL;DR

This paper introduces a biologically inspired neural network learning framework called aSTDP, which uses only STDP rules for supervised and unsupervised learning, mimicking biological processes and enabling pattern prediction and generation.

Contribution

The work presents a novel approximate STDP framework that eliminates the need for global loss functions and integrates derivative-based targets to enhance training efficiency.

Findings

Effective on MNIST for classification

Capable of pattern generation without extra configuration

Uses local learning rules similar to biological neurons

Abstract

Spike-timing dependent plasticity in biological neural networks has been proven to be important during biological learning process. 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 introduce approximate STDP, a new neural networks learning framework more similar to the biological learning process. It uses only STDP rules for supervised and unsupervised learning, every neuron distributed learn patterns and don' t need a global loss or other supervised information. We also use a numerical way to approximate the derivatives of each neuron in order to better use SDTP learning and use the derivatives to set a target for neurons to accelerate training and testing process. The framework can make predictions or generate patterns in one model without additional configuration. Finally, we verified our framework on MNIST dataset for classification and generation tasks.