Towards Trainable Media: Using Waves for Neural Network-Style Training
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- September 2015
- DOI:
- 10.48550/arXiv.1510.03776
- arXiv:
- arXiv:1510.03776
- Bibcode:
- 2015arXiv151003776H
- Keywords:
-
- Computer Science - Neural and Evolutionary Computing;
- Physics - Optics
- E-Print:
- submitted to Scientific Reports