Annealing-inspired training of an optical neural network with ternary weights
Abstract Artificial neural networks (ANNs) represent a fundamentally connectionist and distributed approach to computing, and as such they differ from classical computers that utilize the von Neumann architecture. This has revived research interest in new unconventional hardware for more efficient A...
Saved in:
| Main Authors: | Anas Skalli, Mirko Goldmann, Nasibeh Haghighi, Stephan Reitzenstein, James A. Lott, Daniel Brunner |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Communications Physics |
| Online Access: | https://doi.org/10.1038/s42005-025-01972-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
A spiking photonic neural network of 40 000 neurons, trained with latency and rank-order coding for leveraging sparsity
by: Ria Talukder, et al.
Published: (2025-01-01) -
Quantum-annealing-inspired algorithms for multijet clustering
by: Hideki Okawa, et al.
Published: (2025-05-01) -
Thermal Annealing Effect on Poly(3-hexylthiophene): Fullerene:Copper-Phthalocyanine Ternary Photoactive Layer
by: H. Derouiche, et al.
Published: (2013-01-01) -
Quantum-Inspired Genetic Algorithm Based on Simulated Annealing for Combinatorial Optimization Problem
by: Wanneng Shu
Published: (2009-01-01) -
Static Properties of 980 nm Vertical Cavity Surface Emitting Lasers With Different Monolithic High Refractive Index Contrast Grating Mirror Designs
by: Niels Heermeier, et al.
Published: (2025-01-01)