Aspect of Information in Classical and Quantum Neural Networks

APA

Shen, H. (2020). Aspect of Information in Classical and Quantum Neural Networks. Perimeter Institute for Theoretical Physics. https://pirsa.org/20020052

MLA

Shen, Huitao. Aspect of Information in Classical and Quantum Neural Networks. Perimeter Institute for Theoretical Physics, Feb. 03, 2020, https://pirsa.org/20020052

BibTex

          @misc{ scivideos_PIRSA:20020052,
            doi = {10.48660/20020052},
            url = {https://pirsa.org/20020052},
            author = {Shen, Huitao},
            keywords = {Quantum Matter},
            language = {en},
            title = {Aspect of Information in Classical and Quantum Neural Networks},
            publisher = {Perimeter Institute for Theoretical Physics},
            year = {2020},
            month = {feb},
            note = {PIRSA:20020052 see, \url{https://scivideos.org/pirsa/20020052}}
          }
          

Huitao Shen Massachusetts Institute of Technology (MIT) - Department of Physics

Source Repository PIRSA

Abstract

I’ll talk about two independent works on classical and quantum neural networks connected by information theory. In the first part of the talk, I’ll treat sequence models as one-dimensional classical statistical mechanical systems and analyze the scaling behavior of mutual information. I'll provide a new perspective on why recurrent neural networks are not good at natural language processing. In the second part of the talk, I’ll study information scrambling dynamics when quantum neural networks are trained by classical gradient descent algorithm. For many problems, this hybrid quantum-classical training process consists of two stages where information scrambles very differently in the network.