Home * People * Peter H. Jin

Peter H. Jin,
an American computer scientist affiliated with the University of California, Berkeley. His research is on deep neural networks and Monte Carlo tree search. In 2015, along with his advisor Kurt Keutzer ^[1], he published on a MCTS based Go playing program which uses convolutional networks in all parts, exploring the Monte-Carlo search tree using Thompson sampling and a convolutional network, and evaluates convolutional network based rollouts on a GPU ^[2], a revised version represented by Peter Jin at CG 2016 ^[3].

Selected Publications

^[4]

• Peter H. Jin, Kurt Keutzer (2015). Convolutional Monte Carlo Rollouts in Go. arXiv:1512.03375
• Peter H. Jin, Kurt Keutzer (2016). Convolutional Monte Carlo Rollouts for Computer Go. CG 2016

External Links

• Peter H. Jin
• Peter Jin | LinkedIn
• peterhj (Peter H. Jin) · GitHub

References

1. ^ Kurt Keutzer's Home Page - Current Doctoral Students
2. ^ Peter H. Jin, Kurt Keutzer (2015). Convolutional Monte Carlo Rollouts in Go. arXiv:1512.03375
3. ^ Computers and Games 2016 Leiden - Videos
4. ^ dblp: Peter H. Jin

What links here?

Up one level