Attention-Augmented Machine Memory

Xin Lin, Guoqiang Zhong*, Kang Chen, Qingyang Li, Kaizhu Huang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Attention mechanism plays an important role in the perception and cognition of human beings. Among others, many machine learning models have been developed to memorize the sequential data, such as the Long Short-Term Memory (LSTM) network and its extensions. However, due to lack of the attention mechanism, they cannot pay special attention to the important parts of the sequences. In this paper, we present a novel machine learning method called attention-augmented machine memory (AAMM). It seamlessly integrates the attention mechanism into the memory cell of LSTM. As a result, it facilitates the network to focus on valuable information in the sequences and ignore irrelevant information during its learning. We have conducted experiments on two sequence classification tasks for pattern classification and sentiment analysis, respectively. The experimental results demonstrate the advantages of AAMM over LSTM and some other related approaches. Hence, AAMM can be considered as a substitute of LSTM in the sequence learning applications.

Original languageEnglish
Pages (from-to)751-760
Number of pages10
JournalCognitive Computation
Volume13
Issue number3
DOIs
Publication statusPublished - May 2021

Keywords

  • Attention mechanism
  • Attention-augmented machine memory (AAMM)
  • Long short-term memory (LSTM)
  • Machine learning
  • Sequence classification

Fingerprint

Dive into the research topics of 'Attention-Augmented Machine Memory'. Together they form a unique fingerprint.

Cite this