Reliable and Fast Recurrent Neural Network Architecture Optimization

06/29/2021

∙

by   Andrés Camero, et al.

∙

0

∙

share

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.