3 papers
cs.NE2019
Reservoir-size dependent learning in analogue neural networks
Xavier Porte, Louis Andreoli, Maxime Jacquot +2
The implementation of artificial neural networks in hardware substrates is a major interdisciplinary enterprise. Well suited candidates for physical implementations must combine no…
cs.ET2019
Fundamental aspects of noise in analog-hardware neural networks
Nadezhda Semenova, Xavier Porte, Louis Andreoli +3
We study and analyze the fundamental aspects of noise propagation in recurrent as well as deep, multi-layer networks. The main focus of our study are neural networks in analogue ha…
physics.optics2019
Diffractive coupling for photonic networks: how big can we go?
Sheler Maktoobi, Luc Froehly, Louis Andreoli +4
Photonic networks are considered a promising substrate for high-performance future computing systems. Compared to electronics, photonics has significant advantages for a fully para…