# A Brain-inspired Algorithm for Training Highly Sparse Neural Networks

## TL;DR

This paper introduces a biologically inspired sparse neural network training algorithm, CTRE, which evolves network topology based on neuron behavior using cosine similarity, avoiding dense gradient calculations and outperforming existing methods.

## Contribution

The paper presents a novel sparse training method, CTRE, that evolves network topology based on neuron importance, inspired by biological brain principles, and does not require dense gradient computation.

## Key findings

- Outperforms state-of-the-art sparse training algorithms in high sparsity scenarios.
- Demonstrates effectiveness across diverse datasets including tabular, image, and text.
- Achieves significant performance gains with extremely sparse neural networks.

## Abstract

Sparse neural networks attract increasing interest as they exhibit comparable performance to their dense counterparts while being computationally efficient. Pruning the dense neural networks is among the most widely used methods to obtain a sparse neural network. Driven by the high training cost of such methods that can be unaffordable for a low-resource device, training sparse neural networks sparsely from scratch has recently gained attention. However, existing sparse training algorithms suffer from various issues, including poor performance in high sparsity scenarios, computing dense gradient information during training, or pure random topology search. In this paper, inspired by the evolution of the biological brain and the Hebbian learning theory, we present a new sparse training approach that evolves sparse neural networks according to the behavior of neurons in the network. Concretely, by exploiting the cosine similarity metric to measure the importance of the connections, our proposed method, Cosine similarity-based and Random Topology Exploration (CTRE), evolves the topology of sparse neural networks by adding the most important connections to the network without calculating dense gradient in the backward. We carried out different experiments on eight datasets, including tabular, image, and text datasets, and demonstrate that our proposed method outperforms several state-of-the-art sparse training algorithms in extremely sparse neural networks by a large gap. The implementation code is available on https://github.com/zahraatashgahi/CTRE