摘要
谷歌的围棋系统阿法狗(AlphaGo)在三月的比赛中以4:1的成绩击败了围棋世界冠军李世石,大大超过了许多人对计算机围棋程序何时能赶上人类职业高手的预期(约10～30年).本文在技术层面分析了阿法狗系统的组成部分,并基于它过去的公开对局预测了它可能的弱点.
In March 2016, the AlphaGo system from Google Deep Mind beat the World Go Champion Lee Sedol 4：1 in a historic five-game match. This is a giant leap filling the gap between Go AI and top human professional players, which was once regarded to be filled in at least 10~30 years. In this paper, based on published results [Silver et al., 2016], i analyze the components of Alpha Go and predict its potential technical weakness based on the public games of Alpha Go.
出处
《自动化学报》
EI
CSCD
北大核心
2016年第5期671-675,共5页
Acta Automatica Sinica
关键词
深度学习
深度卷积神经网络
计算机围棋
强化学习
阿法狗
Deep learning
deep convolutional neural network
computer Go
reinforcement learning
AlphaGo
