Random Error Sampling-based Recurrent Neural Network Architecture Optimization

TL;DR

This paper introduces RESN, a training-free neuroevolutionary method using random error sampling to efficiently optimize recurrent neural network architectures, achieving state-of-the-art results with reduced computational cost.

Contribution

The paper presents RESN, a novel training-free evolutionary algorithm that significantly reduces architecture optimization time while maintaining high performance.

Findings

Achieves state-of-the-art error performance on prediction tasks.

Reduces architecture optimization time by 50%.

Validates effectiveness across three prediction problems.

Abstract

Recurrent neural networks are good at solving prediction problems. However, finding a network that suits a problem is quite hard because their performance is strongly affected by their architecture configuration. Automatic architecture optimization methods help to find the most suitable design, but they are not extensively adopted because of their high computational cost. In this work, we introduce the Random Error Sampling-based Neuroevolution (RESN), an evolutionary algorithm that uses the mean absolute error random sampling, a training-free approach to predict the expected performance of an artificial neural network, to optimize the architecture of a network. We empirically validate our proposal on three prediction problems, and compare our technique to training-based architecture optimization techniques and to neuroevolutionary approaches. Our findings show that we can achieve state-of-the-art error performance and that we reduce by half the time needed to perform the optimization.