Photonic reservoir computer based on frequency multiplexing
| Autor: | Lorenz Butschek, Akram Akrout, Evangelia Dimitriadou, Alessandro Lupo, Marc Haelterman, Serge Massar |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Neurons Optics and Photonics Photons Computers FOS: Physical sciences Computer Science - Neural and Evolutionary Computing Neural and Evolutionary Computing (cs.NE) Neural Networks Computer Atomic and Molecular Physics and Optics Optics (physics.optics) Physics - Optics |
| Zdroj: | Optics Letters |
| Popis: | Reservoir computing is a brain inspired approach for information processing, well suited to analogue implementations. We report a photonic implementation of a reservoir computer that exploits frequency domain multiplexing to encode neuron states. The system processes 25 comb lines simultaneously (i.e. 25 neurons), at a rate of 20 MHz. We illustrate performances on two standard benchmark tasks: channel equalization and time series forecasting. We also demonstrate that frequency multiplexing allows output weights to be implemented in the optical domain, through optical attenuation. We discuss the perspectives for high speed high performance low footprint implementations. 19 pages. Published version, including supplementary material |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|