Minimal Gated Unit for Recurrent Neural Networks

Abstract

Recently recurrent neural networks (RNN) has been very successful in handling sequence data. However, understanding RNN and finding the best practices for RNN is a difficult task, partly because there are many competing and complex hidden units (such as LSTM and GRU). We propose a gated unit for RNN, named as Minimal Gated Unit (MGU), since it only contains one gate, which is a minimal design among all gated hidden units. The design of MGU benefits from evaluation results on LSTM and GRU in the literature. Experiments on various sequence data show that MGU has comparable accuracy with GRU, but has a simpler structure, fewer parameters, and faster training. Hence, MGU is suitable in RNN's applications. Its simple architecture also means that it is easier to evaluate and tune, and in principle it is easier to study MGU's properties theoretically and empirically.

References in corpus (1)

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation

Cited by in corpus (5)

• Light Gated Recurrent Units for Speech Recognition
• A Flexible Approach to Automated RNN Architecture Generation
• Simplified Minimal Gated Unit Variations for Recurrent Neural Networks
• Topos and Stacks of Deep Neural Networks
• Notes on Pure Dataflow Matrix Machines: Programming with Self-referential Matrix Transformations