Circuit Routing Using Deep Neural Networks and Tree Search
Circuit routing is a fundamental problem in designing electronic systems such as integrated circuits (ICs) and printed circuit boards (PCBs) which form the hardware of electronics and computers. Like finding paths between pairs of locations, circuit routing generates traces of wires to connect contacts or leads of circuit components. It is challenging because finding paths between dense and massive electronic components involves a very large search space. Existing solutions are either manually designed with domain knowledge or tailored to specific constraints in the circuit design, hence, difficult to adapt to new problems or design needs.
Our research focuses on a general routing approach. We model the circuit routing as a sequential decision-making problem and solve it by combining Monte Carlo tree search (MCTS) with deep neural networks (DNNs).
Bio: Youbiao He is a PhD student in Computer Science at Iowa State University. He received his Master’s in Electrical Engineering in 2017 at The University of Akron and the B.E. degree in Electrical Engineering at Dalian University of Technology, China, in 2013. His research interests include reinforcement learning and its applications, circuit routing and high performance computing and I/O scheduling.