Brain-inspired learning in artificial neural networks: a review

TL;DR

This review explores how incorporating biologically inspired learning mechanisms into artificial neural networks can improve their capabilities and bring us closer to understanding intelligence, highlighting current methods, challenges, and future directions.

Contribution

It provides a comprehensive overview of brain-inspired learning methods in ANNs, emphasizing biologically plausible mechanisms like synaptic plasticity and discussing future research avenues.

Findings

Biologically plausible mechanisms can enhance ANN capabilities.

Synaptic plasticity offers promising improvements in learning.

Future research directions are identified for advancing brain-inspired ANNs.

Abstract

Artificial neural networks (ANNs) have emerged as an essential tool in machine learning, achieving remarkable success across diverse domains, including image and speech generation, game playing, and robotics. However, there exist fundamental differences between ANNs' operating mechanisms and those of the biological brain, particularly concerning learning processes. This paper presents a comprehensive review of current brain-inspired learning representations in artificial neural networks. We investigate the integration of more biologically plausible mechanisms, such as synaptic plasticity, to enhance these networks' capabilities. Moreover, we delve into the potential advantages and challenges accompanying this approach. Ultimately, we pinpoint promising avenues for future research in this rapidly advancing field, which could bring us closer to understanding the essence of intelligence.