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

arXiv: https://arxiv.org/abs/1903.07138 · HTML: https://mlsanity.com/paper/1903.07138/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2019.

## Built on by (most cited first, 8 of 8)

- [Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training](https://mlsanity.com/paper/2306.12230/) (2023)
- [Supervised Feature Selection with Neuron Evolution in Sparse Neural Networks](https://mlsanity.com/paper/2303.07200/) (2023)
- [Unveiling the Power of Sparse Neural Networks for Feature Selection](https://mlsanity.com/paper/2408.04583/) (2024)
- [ManiFeSt: Manifold-based Feature Selection for Small Data Sets](https://mlsanity.com/paper/2207.08574/) (2022)
- [Adaptive Sparsity Level during Training for Efficient Time Series Forecasting with Transformers](https://mlsanity.com/paper/2305.18382/) (2023)
- [Boosting Robustness in Preference-Based Reinforcement Learning with Dynamic Sparsity](https://mlsanity.com/paper/2406.06495/) (2024)
- [Switch-Based Multi-Part Neural Network](https://mlsanity.com/paper/2504.18241/) (2025)
- [Constrained Hebbian Learning Supports Efficient Representational Allocation under Structural Constraints](https://mlsanity.com/paper/2607.16027/) (2026)

## Abstract (arXiv)

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