# Genetic Algorithms for Evolving Deep Neural Networks

arXiv: https://arxiv.org/abs/1711.07655 · HTML: https://mlsanity.com/paper/1711.07655/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2017.

## Built on by (most cited first, 5 of 5)

- [Training Stacked Denoising Autoencoders for Representation Learning](https://mlsanity.com/paper/2102.08012/) (2021)
- [Category-wise Fine-Tuning: Resisting Incorrect Pseudo-Labels in Multi-Label Image Classification with Partial Labels](https://mlsanity.com/paper/2401.16991/) (2024)
- [A new Sparse Auto-encoder based Framework using Grey Wolf Optimizer for Data Classification Problem](https://mlsanity.com/paper/2201.12493/) (2022)
- [Towards evolution of Deep Neural Networks through contrastive Self-Supervised learning](https://mlsanity.com/paper/2406.14525/) (2024)
- [Deep Learning Based Superconductivity: Prediction and Experimental Tests](https://mlsanity.com/paper/2412.13012/) (2024)

## Abstract (arXiv)

In recent years, deep learning methods applying unsupervised learning to train deep layers of neural networks have achieved remarkable results in numerous fields. In the past, many genetic algorithms based methods have been successfully applied to training neural networks. In this paper, we extend previous work and propose a GA-assisted method for deep learning. Our experimental results indicate that this GA-assisted approach improves the performance of a deep autoencoder, producing a sparser neural network.