vix.ing · top · new · best · stats · spec

Towards Trainable Media: Using Waves for Neural Network-Style Training

2015/09/30 by Michiel Hermans, Hermans, Michiel, Thomas Van Vaerenbergh +1 · 2 voices
Computer Science · Physics and Astronomy · #FOS: Computer and information sciences #FOS: Physical sciences #Neural and Evolutionary Computing (cs.NE) #Optics (physics.optics) #cs.NE #physics.optics

paper · pdf · doi:10.48550/arxiv.1510.03776

submitted to Scientific Reports

arxiv created 2015/09/30 · arxiv published 2015/09/30 · arxiv updated 2015/10/14

Abstract

In this paper we study the concept of using the interaction between waves and a trainable medium in order to construct a matrix-vector multiplier. In particular we study such a device in the context of the backpropagation algorithm, which is commonly used for training neural networks. Here, the weights of the connections between neurons are trained by multiplying a `forward' signal with a backwards propagating `error' signal. We show that this concept can be extended to trainable media, where the gradient for the local wave number is given by multiplying signal waves and error waves. We provide a numerical example of such a system with waves traveling freely in a trainable medium, and we discuss a potential way to build such a device in an integrated photonics chip.

Discussions

Related