# Regularized Evolutionary Algorithm for Dynamic Neural Topology Search

arXiv: https://arxiv.org/abs/1905.06252 · HTML: https://mlsanity.com/paper/1905.06252/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 May 2019.

## Built on by (most cited first, 1 of 1)

- [Efficient Neural Architecture Search with Performance Prediction](https://mlsanity.com/paper/2108.01854/) (2021)

## Abstract (arXiv)

Designing neural networks for object recognition requires considerable architecture engineering. As a remedy, neuro-evolutionary network architecture search, which automatically searches for optimal network architectures using evolutionary algorithms, has recently become very popular. Although very effective, evolutionary algorithms rely heavily on having a large population of individuals (i.e., network architectures) and is therefore memory expensive. In this work, we propose a Regularized Evolutionary Algorithm with low memory footprint to evolve a dynamic image classifier. In details, we introduce novel custom operators that regularize the evolutionary process of a micro-population of 10 individuals. We conduct experiments on three different digits datasets (MNIST, USPS, SVHN) and show that our evolutionary method obtains competitive results with the current state-of-the-art.