Random Error Sampling-based Recurrent Neural Network Architecture Optimization
This work addresses the computational bottleneck in neural network architecture optimization for prediction problems, offering a faster alternative to existing methods.
The authors tackled the problem of high computational cost in automatic recurrent neural network architecture optimization by introducing RESN, a training-free evolutionary algorithm that uses random error sampling to predict performance, achieving state-of-the-art error and reducing optimization time by half.
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.