# EDEN: Evolutionary Deep Networks for Efficient Machine Learning

arXiv: https://arxiv.org/abs/1709.09161 · HTML: https://mlsanity.com/paper/1709.09161/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2017.

## Built on by (most cited first, 6 of 6)

- [DQNAS: Neural Architecture Search using Reinforcement Learning](https://mlsanity.com/paper/2301.06687/) (2023)
- [Multiobjective Evolutionary Pruning of Deep Neural Networks with Transfer Learning for improving their Performance and Robustness](https://mlsanity.com/paper/2302.10253/) (2023)
- [Evolutionary Computation for the Design and Enrichment of General-Purpose Artificial Intelligence Systems: Survey and Prospects](https://mlsanity.com/paper/2407.08745/) (2024)
- [An Improved Nearest Neighbour Classifier](https://mlsanity.com/paper/2204.13141/) (2022)
- [Is it conceivable that neurogenesis, neural Darwinism, and species evolution could all serve as inspiration for the creation of evolutionary deep neural networks?](https://mlsanity.com/paper/2304.03122/) (2023)
- [Edge-Native Digitization of Handwritten Marksheets: A Hybrid Heuristic-Deep Learning Framework](https://mlsanity.com/paper/2508.16295/) (2025)

## Abstract (arXiv)

Deep neural networks continue to show improved performance with increasing depth, an encouraging trend that implies an explosion in the possible permutations of network architectures and hyperparameters for which there is little intuitive guidance. To address this increasing complexity, we propose Evolutionary DEep Networks (EDEN), a computationally efficient neuro-evolutionary algorithm which interfaces to any deep neural network platform, such as TensorFlow. We show that EDEN evolves simple yet successful architectures built from embedding, 1D and 2D convolutional, max pooling and fully connected layers along with their hyperparameters. Evaluation of EDEN across seven image and sentiment classification datasets shows that it reliably finds good networks -- and in three cases achieves state-of-the-art results -- even on a single GPU, in just 6-24 hours. Our study provides a first attempt at applying neuro-evolution to the creation of 1D convolutional networks for sentiment analysis including the optimisation of the embedding layer.