stat946w18/Tensorized LSTMs: Difference between revisions

From statwiki
Jump to navigation Jump to search
Line 12: Line 12:
* 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 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 time step are merged into temporal computations of the sequence.  
* By delaying the output, the network can be deepened implicitly with little additional runtime since deep computations for each time step are merged into temporal computations of the sequence.  


Also, the paper has presented presented experiments conducted on five challenging sequence learning tasks show the potential of the proposed model.
Also, the paper has presented presented experiments conducted on five challenging sequence learning tasks show the potential of the proposed model.

Revision as of 15:45, 14 March 2018

Presented by

Chen, Weishi(Edward)

Introduction

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 (illustrations will be provided later).


However, usually the LSTM model introduces additional parameters, while LSTM with additional layers and wider layers increases the time required for model training and evaluation. As an alternative, the paper <Wider and Deeper, Cheaper and Faster: Tensorized LSTMs for Sequence Learning> has proposed a model based on LSTM call 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 time step are merged into temporal computations of the sequence.


Also, the paper has presented presented experiments conducted on five challenging sequence learning tasks show the potential of the proposed model.