Reliable and Fast Recurrent Neural Network Architecture Optimization

This article introduces Random Error Samplingbased 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.

[1]  Enrique Alba,et al.  Random error sampling-based recurrent neural network architecture optimization , 2019, Eng. Appl. Artif. Intell..

[2]  Travis Desell,et al.  Evolving Recurrent Neural Networks for Time Series Data Prediction of Coal Plant Parameters , 2019, EvoApplications.

[3]  Travis Desell,et al.  Investigating recurrent neural network memory structures using neuro-evolution , 2019, GECCO.

[4]  Enrique Alba,et al.  BIN-CT: Urban Waste Collection based in Predicting the Container Fill Level , 2018, Biosyst..

[5]  Enrique Alba,et al.  Waste Generation Prediction in Smart Cities Through Deep Neuroevolution , 2018, ICSC-Cities.

[6]  Enrique Alba,et al.  Low-Cost Recurrent Neural Network Expected Performance Evaluation , 2018, ArXiv.

[7]  Elliot Meyerson,et al.  Evolutionary architecture search for deep multitask networks , 2018, GECCO.

[8]  Mingyuan Zhang,et al.  Short-term load forecasting based on multivariate time series prediction and weighted neural network with random weights and kernels , 2018, Cluster Computing.

[9]  Václav Snásel,et al.  Metaheuristic design of feedforward neural networks: A review of two decades of research , 2017, Eng. Appl. Artif. Intell..

[10]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[11]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[12]  Razvan Pascanu,et al.  On the difficulty of training recurrent neural networks , 2012, ICML.

[13]  Ming-Wei Chang,et al.  Load Forecasting Using Support Vector Machines: A Study on EUNITE Competition 2001 , 2004, IEEE Transactions on Power Systems.

[14]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.