Reliable and Fast Recurrent Neural Network Architecture Optimization
arXiv:2106.15295
Abstract
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.
References in corpus (6)
- Adam: A Method for Stochastic Optimization
- On the difficulty of training Recurrent Neural Networks
- Metaheuristic Design of Feedforward Neural Networks: A Review of Two Decades of Research
- BIN-CT: Urban Waste Collection based in Predicting the Container Fill Level
- Random Error Sampling-based Recurrent Neural Network Architecture Optimization
- Low-Cost Recurrent Neural Network Expected Performance Evaluation