Podcasts Technology Practical AI: Machine Learning, Data Science Reinforcement learning for chip design

Reinforcement learning for chip design

Published: April 27, 2020, 7:30 p.m.

b'Daniel and Chris have a fascinating discussion with Anna Goldie and Azalia Mirhoseini from Google Brain about the use of reinforcement learning for chip floor planning - or placement - in which many new designs are generated, and then evaluated, to find an optimal component layout. Anna and Azalia also describe the use of graph convolutional neural networks in their approach.'