# EvoAAA: An evolutionary methodology for automated neural autoencoder architecture search

arXiv: https://arxiv.org/abs/2301.06047 · HTML: https://mlsanity.com/paper/2301.06047/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 109 references that are in the map.
- First posted on arXiv 15 Jan 2023.

## Builds on (most cited first, 8 of 8)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [NAS-Bench-101: Towards Reproducible Neural Architecture Search](https://mlsanity.com/paper/1902.09635/) (2019)
- [cuDNN: Efficient Primitives for Deep Learning](https://mlsanity.com/paper/1410.0759/) (2014)
- [Auto-Keras: An Efficient Neural Architecture Search System](https://mlsanity.com/paper/1806.10282/) (2018)
- [A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines](https://mlsanity.com/paper/1801.01586/) (2018)
- [AEkNN: An AutoEncoder kNN-based classifier with built-in dimensionality reduction](https://mlsanity.com/paper/1802.08465/) (2018)
- [A snapshot on nonstandard supervised learning problems: taxonomy, relationships and methods](https://mlsanity.com/paper/1811.12044/) (2018)
- [A Showcase of the Use of Autoencoders in Feature Learning Applications](https://mlsanity.com/paper/2005.04321/) (2020)

## Built on by (most cited first, 2 of 2)

- [Evolutionary Computation for the Design and Enrichment of General-Purpose Artificial Intelligence Systems: Survey and Prospects](https://mlsanity.com/paper/2407.08745/) (2024)
- [Automated univariate time series forecasting with regression trees](https://mlsanity.com/paper/2602.00077/) (2026)

## Abstract (arXiv)

Machine learning models work better when curated features are provided to them. Feature engineering methods have been usually used as a preprocessing step to obtain or build a proper feature set. In late years, autoencoders (a specific type of symmetrical neural network) have been widely used to perform representation learning, proving their competitiveness against classical feature engineering algorithms. The main obstacle in the use of autoencoders is finding a good architecture, a process that most experts confront manually. An automated autoencoder architecture search procedure, based on evolutionary methods, is proposed in this paper. The methodology is tested against nine heterogeneous data sets. The obtained results show the ability of this approach to find better architectures, able to concentrate most of the useful information in a minimized coding, in a reduced time.