A comparison of LSTM and GRU networks for learning symbolic sequences

Abstract

We explore the architecture of recurrent neural networks (RNNs) by studying the complexity of string sequences it is able to memorize. Symbolic sequences of different complexity are generated to simulate RNN training and study parameter configurations with a view to the network's capability of learning and inference. We compare Long Short-Term Memory (LSTM) networks and gated recurrent units (GRUs). We find that an increase in RNN depth does not necessarily result in better memorization capability when the training time is constrained. Our results also indicate that the learning rate and the number of units per layer are among the most important hyper-parameters to be tuned. Generally, GRUs outperform LSTM networks on low-complexity sequences while on high-complexity sequences LSTMs perform better.

References in corpus (2)

• TimeNet: Pre-trained deep recurrent neural network for time series classification
• The Effectiveness of Discretization in Forecasting: An Empirical Study on Neural Time Series Models

Cited by in corpus (4)

• Modeling and Predicting Transistor Aging under Workload Dependency using Machine Learning
• A Comparison of Deep Learning Architectures for Spacecraft Anomaly Detection
• A novel stacked hybrid autoencoder for imputing LISA data gaps
• Mobile Traffic Prediction at the Edge Through Distributed and Deep Transfer Learning