Photonic Integrated Recurrent Neural Network Based on Frequency Multiplexing

Jan 12, 2023
Facebook X LinkedIn Email
Login  Register
About This Webinar
Reservoir Computers (RCs) are brain-inspired algorithms based on recurrent neural networks where only output weights are tuned, while internal weights remain untrained. VLC Photonics recently demonstrated a photonic frequency-multiplexing RC encoding neurons in the lines of a frequency comb. Additionally, VLC demonstrated a single-layer feed-forward neural network based on a similar frequency-multiplexing principle. Jonuzi's presentation covers the design for an integrated optical output layer for such frequency-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.

***This presentation premiered during the 2023 Photonics Spectra Conference. For more information on Photonics Media conferences, visit

About the presenter

Tigers JonuziTigers Jonuzi (M) obtained the M.Sc in Engineering Physics at the university of Politencnico di Milano (Polimi) with a thesis, carried on in the Photonic Devices Group, on the design and control of photonic integrated circuits for light beam manipulation part of H2020 Super-Pixels FET project.

He is co-author of conference papers spanning analog photonic computing and optical beam manipulation. He is currently attending an industrial Ph.D., hosted by VLCphotonics S.L., working in the POST-DIGITAL project where his research focuses on the photonic device integration of neuromorphic computing, spanning from reservoir to convolutional neural network schemes, defining an efficient approach for harnessing and suppressing nonlinear optical processes.
photonic integrated circuitsPICsneural networks
We use cookies to improve user experience and analyze our website traffic as stated in our Privacy Policy. By using this website, you agree to the use of cookies unless you have disabled them.