TY - GEN
T1 - Improve the performance of neural network training with accurate information
T2 - 2019 International Conference on Advanced Information Science and System, AISS 2019
AU - Huang, Shih Hao
AU - Chen, Chih Hung
AU - Lin, Shun Shii
N1 - Funding Information:
This research was funded by the Ministry of Science and Technology (R.O.C.) and Qualcomm Incorporated under grants MOST 108-2221-E-003-011-MY3, MOST 108-2634-F-259-001- through Pervasive Artificial Intelligence Research and NAT-414697.
Funding Information:
This research was funded by the Ministry of Science and Technology (R.O.C.) and Qualcomm Incorporated under grants MOST 108-2221-E-003-011-MY3, MOST 108-2634-F-259-001-through Pervasive Artificial Intelligence Research (PAIR) Labs, and NAT-414697.
Publisher Copyright:
© 2019 Association for Computing Machinery.
PY - 2019/11/15
Y1 - 2019/11/15
N2 - 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.
AB - 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.
KW - AlphaZero
KW - Connect6
KW - Deep learning
KW - Neural network
KW - Reinforcement learning
UR - http://www.scopus.com/inward/record.url?scp=85123039930&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85123039930&partnerID=8YFLogxK
U2 - 10.1145/3373477.3373703
DO - 10.1145/3373477.3373703
M3 - Conference contribution
AN - SCOPUS:85123039930
T3 - ACM International Conference Proceeding Series
BT - Proceedings of the International Conference on Advanced Information Science and System, AISS 2019
PB - Association for Computing Machinery
Y2 - 15 November 2019 through 17 November 2019
ER -