The 81st JSAP Autumn Meeting, 2020

Presentation information

Oral presentation

FS Focused Session "AI Electronics" » FS.1 Focused Session "AI Electronics"

[9p-Z28-1~19] FS.1 Focused Session "AI Electronics"

Wed. Sep 9, 2020 1:30 PM - 7:00 PM Z28

Tetsuya Asai(Hokkaido Univ.), Nakajima Mitsumasa(NTT)

5:15 PM - 5:30 PM

[9p-Z28-13] Continuous Representation of Neural Network by Schrödinger Equation

Mitsumasa Nakajima1, Kenji Tanaka1, Toshikazu Hashimoto1 (1.NTT Device Technology Labs.)

Keywords:Neuromorphic, Neural network, Optical circuit

Recently, neural ordinary differential equations (Neural-ODEs), which is a continuous representation of deep neural networks (DNNs), have been gathering much attentions. In this framework, the differential equation x(t+1)=f[x(t),θ,t] is considered as an evolution of the layers in the DNNs. The outputs and weights are trained by using standard ODE solvers. In this paper, we propose the continious representation of the neural network based on the Schrodinger equation, which is used for modeling lightwave propagations in optical waveguides. The trained (i.e. designed) network is physically transferrable throught the refractive index.