Physics informed machine learning has a long history goes back to the statistical physics of spin glasses. We argue that in a modern age, quantum physics can be equally inspirational by exploiting the mind-provoking analogy between the "image space" and the Hilbert space. Exchanging of ideas, insights, techniques, and even intuitions developed for machine learning and quantum physics will cross-fertilize both research fields. In particular, I shall talk about quantum-inspired generative models using tensor networks and actual quantum circuits. I will end by commenting on the future of “Quantum Software 2.0” empowered by differentiable programming techniques.
报告人简介：王磊，2006年本科毕业于南京大学，2011年获中科院物理研究所博士学位。此后在瑞士苏黎世联邦理工学院从事计算量子物理的博士后研究。从2016年3月起在中科院物理研究所工作。目前主要的研究兴趣是深度学习的理论与应用以及量子多体计算。热爱编程、崇尚技术。