He, Z; Gao, S; Xiao, L; Barber, D; (2017) Wider and Deeper, Cheaper and Faster: Tensorized LSTMs for Sequence Learning. In: Guyon, I and Luxburg, UV and Bengio, S and Wallach, H and Fergus, R and Vishwanathan, S and Garnett, R, (eds.) Advances in Neural Information Processing Systems 30 (NIPS 2017) pre-proceedings. NIPS Proceedings: Long Beach, CA, USA.

Preview

Text Barber_6606-wider-and-deeper-cheaper-and-faster-tensorized-lstms-for-sequence-learning.pdf - Published Version Download (3MB) | Preview

Abstract

Long Short-Term Memory (LSTM) is a popular approach to boosting the ability of Recurrent Neural Networks to store longer term temporal information. The capacity of an LSTM network can be increased by widening and adding layers. However, usually the former introduces additional parameters, while the latter increases the runtime. As an alternative we propose the Tensorized LSTM in which the hidden states are represented by tensors and updated via a cross-layer convolution. By increasing the tensor size, the network can be widened efficiently without additional parameters since the parameters are shared across different locations in the tensor; by delaying the output, the network can be deepened implicitly with little additional runtime since deep computations for each timestep are merged into temporal computations of the sequence. Experiments conducted on five challenging sequence learning tasks show the potential of the proposed model.

Download activity - last month

Export as XMLCSVJSON

Download activity - last 12 months

Export as XMLCSVJSON

Downloads by country - last 12 months

Export as CSVXMLJSON

Archive Staff Only

View Item