• Citer

Integrated optical output layer for a reservoir computer based on frequency multiplexing

par Jonuzi, Tigers;Lupo, Alessandro ;Soriano, Miguel Cornelles;David Domenech Gomez, J.;Massar, Serge
Référence SPIE OPTO(2023: San Francisco, California, United States), AI and Optical Data Sciences IV AI and Optical Data Sciences IV, SPIE, Vol. 12438, page (124380)
Publication Publié, 2023

Publication dans des actes

• Accès en ligne
• Détails
• Contenu
• Statistiques

Résumé :

Reservoir Computers (RCs) are brain-inspired algorithms based on recurrent neural networks where only output weights are tuned, while internal weights remain untrained. We recently demonstrated a photonic frequency-multiplexing RC encoding neurons in the lines of a frequency comb. We also demonstrated a single-layer feed-forward neural network based on a similar frequency-multiplexing principle. Here we present the design for an integrated optical output layer for such frequency multiplexing based photonic neural networks. The all-optical output layer uses wavelength (de)multiplexers and wavelength converters to apply signed weights to neurons encoded in comb lines.