# Reliable and Fast Recurrent Neural Network Architecture Optimization

arXiv: https://arxiv.org/abs/2106.15295 · HTML: https://mlsanity.com/paper/2106.15295/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 14 references that are in the map.
- First posted on arXiv 29 Jun 2021.

## Builds on (most cited first, 7 of 7)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Evolutionary Architecture Search For Deep Multitask Networks](https://mlsanity.com/paper/1803.03745/) (2018)
- [Metaheuristic Design of Feedforward Neural Networks: A Review of Two Decades of Research](https://mlsanity.com/paper/1705.05584/) (2017)
- [Investigating Recurrent Neural Network Memory Structures using Neuro-Evolution](https://mlsanity.com/paper/1902.02390/) (2019)
- [Low-Cost Recurrent Neural Network Expected Performance Evaluation](https://mlsanity.com/paper/1805.07159/) (2018)
- [BIN-CT: Urban Waste Collection based in Predicting the Container Fill Level](https://mlsanity.com/paper/1807.01603/) (2018)

## Abstract (arXiv)

This article introduces Random Error Sampling-based Neuroevolution (RESN), a novel automatic method to optimize recurrent neural network architectures. RESN combines an evolutionary algorithm with a training-free evaluation approach. The results show that RESN achieves state-of-the-art error performance while reducing by half the computational time.