# Bio-Inspired Neural Network Dynamics-Aware Reinforcement Learning for Spiking Neural Network

## TL;DR

This paper explores using reinforcement learning inspired by biology to improve training of spiking neural networks, which could lead to more human-like and interpretable AI.

## Contribution

The paper introduces bio-inspired reinforcement learning strategies to enhance training of large-scale spiking neural networks.

## Key findings

- Using reinforcement learning to focus on neural network dynamics improves learning efficiency in spiking neural networks.
- Bio-inspired strategies show promise for developing effective learning algorithms for complex spiking neural networks.
- The approach could lead to more interpretable and human-like artificial intelligence systems.

## Abstract

Artificial Intelligence (AI) has seen rapid advancements in recent times, finding applications across various sectors and achieving notable successes. However, current AI models based on Deep Convolutional Neural Networks (DNNs) face numerous challenges, particularly a lack of interpretability, which severely restricts their future potential. Spiking Neural Networks (SNNs), considered the third generation of Artificial Neural Networks (ANNs), are at the forefront of brain-inspired AI research. The resemblance between SNNs and biological neural networks offers the potential to create more human-like AI systems with enhanced interpretability, paving the way for more trustworthy AI implementations. Despite this promise, the absence of efficient training methods for large-scale and complex SNNs hampers their broader application. This paper investigates bio-inspired reinforcement learning strategies by examining neural network dynamics during SNN training. The aim is to improve learning efficiency and effectiveness for extensive and intricate SNNs. Our findings suggest that using reinforcement learning to focus on neural network dynamics may be a promising approach for developing learning algorithms for future large-scale SNNs.