.png){kind=icon}
返回
Tensor Train Recurrent Network Language Model Prediction
.png){kind=icon}
OA
AI
DOI：10.1002/sta4.70116.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recurrent neural networks (RNN) such as long-short-term memory (LSTM) networks are essential in a multitude of daily tasks such as speech, language, video and multimodal learning. The shift from cloud to edge computation intensifies the need to contain the growth in size of RNNs. Current research on RNN shows that despite the performance obtained on convolutional neural networks (CNN), keeping a good performance in compressed RNNs is still a challenge. This paper shows that by incorporating informative matrix-normal priors on the tensor weights, tensor-compressed LSTM networks can achieve comparable performance to LSTM networks. Most literature on compression focuses on CNNs using matrix product (MPO) operator tensor trains. However, matrix product state (MPS) tensor trains have more attractive features in terms of storage reduction and computing time for prediction. The present work shows that MPS tensor trains should be at the forefront of LSTM network compression through a theoretical analysis and practical experiments on natural language processing (NLP) tasks.
Keyword:
network compression
probabilistic language models
tensor decomposition
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
S
IF:
0.8
论文数:
58
被引数:
655
机构
引用论文
.png){kind=icon}
分享收藏
分享收藏Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference用于有效的仅整数算术推理的神经网络的量化和训练OAAI
OAAI分享收藏分享收藏
查看更多内容