跳到主要导航 跳到搜索 跳到主要内容

Comparison of Static Neural Network with External Memory and RNNs for Deterministic Context Free Language Learning

  • University of Florida

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

In this paper, a learning model for prediction is introduced by coupling a static neural network with an external stack memory, creating a new type of recurrent system. We analyze the differences between this external memory recurrent network and recurrent neural network, which possesses internal memory. Internal memory remembers the last state while external memory remembers past useful contents. For a specific automaton, the internal memory is needed if the last state is a variable of the state transition function and the external memory is needed if the past content is a variable of state transition function. Our arguments are verified by comparing the prediction accuracy of different models with internal memory, external memory and the combination of them on counting and reversing tasks. The results shows that: Network with an external stack works best for counting tasks since the variables of state transition function is composed of the current input and one past input, while network with the combination of internal and external memory works best for the reversing task since the variables of state transition function is composed of the current input, current state and the past inputs.

源语言英语
主期刊名2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings
出版商Institute of Electrical and Electronics Engineers Inc.
ISBN(电子版)9781509060146
DOI
出版状态已出版 - 10 10月 2018
已对外发布是
活动2018 International Joint Conference on Neural Networks, IJCNN 2018 - Rio de Janeiro, 巴西
期限: 8 7月 2018 → 13 7月 2018

丛书

姓名Proceedings of the International Joint Conference on Neural Networks
卷2018-July

会议

会议2018 International Joint Conference on Neural Networks, IJCNN 2018
国家/地区巴西
市Rio de Janeiro
时期8/07/18 → 13/07/18

学术指纹

探究 'Comparison of Static Neural Network with External Memory and RNNs for Deterministic Context Free Language Learning' 的科研主题。它们共同构成独一无二的学术指纹。

引用此