papers AI Learner
The Github is limit! Click to go to the new site.

Learning Compact Recurrent Neural Networks

2016-04-09
Zhiyun Lu, Vikas Sindhwani, Tara N. Sainath

Abstract

Recurrent neural networks (RNNs), including long short-term memory (LSTM) RNNs, have produced state-of-the-art results on a variety of speech recognition tasks. However, these models are often too large in size for deployment on mobile devices with memory and latency constraints. In this work, we study mechanisms for learning compact RNNs and LSTMs via low-rank factorizations and parameter sharing schemes. Our goal is to investigate redundancies in recurrent architectures where compression can be admitted without losing performance. A hybrid strategy of using structured matrices in the bottom layers and shared low-rank factors on the top layers is found to be particularly effective, reducing the parameters of a standard LSTM by 75%, at a small cost of 0.3% increase in WER, on a 2,000-hr English Voice Search task.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1604.02594

PDF

https://arxiv.org/pdf/1604.02594


Similar Posts

Comments