Improve the performance of neural network training with accurate information: Take Connect6 for example

Shih Hao Huang, Zhi-Hong Chen, Shun Shii Lin*

*此作品的通信作者

研究成果: 書貢獻/報告類型會議論文篇章

摘要

DeepMind introduced a general reinforcement learning algorithm called AlphaZero to learn through self-play without any human knowledge. It got a superhuman success not only in Go but also in Chess and Shogi. Nevertheless, AlphaZero needs huge computational resources to train a high quality neural network. Most institutions have no such huge computational resources or cannot invest an enormous number of resources to support a research project. Therefore, this paper proposes to embed accurate information into the training phase for improving the performance of the neural network under limited resources. In competition with Zeta-180, the win rate of FD-60 far surpasses all other modifications. The results of experiments indicate that embedding accurate information into the training-phase can effectively improve the performance of the neural network under limited resources.

原文英語
主出版物標題Proceedings of the International Conference on Advanced Information Science and System, AISS 2019
發行者Association for Computing Machinery
ISBN(電子)9781450372916
DOIs
出版狀態已發佈 - 2019 十一月 15
事件2019 International Conference on Advanced Information Science and System, AISS 2019 - Singapore, 新加坡
持續時間: 2019 十一月 152019 十一月 17

出版系列

名字ACM International Conference Proceeding Series

會議

會議2019 International Conference on Advanced Information Science and System, AISS 2019
國家/地區新加坡
城市Singapore
期間2019/11/152019/11/17

ASJC Scopus subject areas

  • 軟體
  • 人機介面
  • 電腦視覺和模式識別
  • 電腦網路與通信

指紋

深入研究「Improve the performance of neural network training with accurate information: Take Connect6 for example」主題。共同形成了獨特的指紋。

引用此