講演会: Deep limits of residual neural networks, Yves van Gennip 氏

開催日時

2019年7月31日 13時 00分 ～ 2019年7月31日 14時 00分

場所

北海道大学理学部3号館3-307室

講演者

Yves van Gennip 氏 (デルフト工科大学)

Through recent work of Haber and Ruthotto and others, it has been recognised that certain neural network architectures can be interpreted as discretised ordinary differential equations (ODEs). In this talk we will see an application of a method developed by Slepcev and Garcia Trillos which allows us to make this interpretation rigorous in a variational framework: We will show that the training of a residual neural network can be formulated as a constrained discrete variational problem, whose deep layer limit (i.e. #layers –> infinity) is given by a continuum variational problem constrained by an ODE.

This is joint work with Matthew Thorpe.

世話人：浜向 直