We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Boolean learning under noise-perturbations in hardware neural networks.
- Authors
Andreoli, Louis; Porte, Xavier; Chrétien, Stéphane; Jacquot, Maxime; Larger, Laurent; Brunner, Daniel
- Abstract
A high efficiency hardware integration of neural networks benefits from realizing nonlinearity, network connectivity and learning fully in a physical substrate. Multiple systems have recently implemented some or all of these operations, yet the focus was placed on addressing technological challenges. Fundamental questions regarding learning in hardware neural networks remain largely unexplored. Noise in particular is unavoidable in such architectures, and here we experimentally and theoretically investigate its interaction with a learning algorithm using an opto-electronic recurrent neural network. We find that noise strongly modifies the system's path during convergence, and surprisingly fully decorrelates the final readout weight matrices. This highlights the importance of understanding architecture, noise and learning algorithm as interacting players, and therefore identifies the need for mathematical tools for noisy, analogue system optimization.
- Subjects
MACHINE learning; MATHEMATICAL optimization; ARTIFICIAL neural networks; RECURRENT neural networks; HARDWARE
- Publication
Nanophotonics (21928606), 2020, Vol 9, Issue 14, p4139
- ISSN
2192-8606
- Publication type
Article
- DOI
10.1515/nanoph-2020-0171