Programmable Tanh- and ELU-Based Photonic Neurons in Optics-Informed Neural Networks

• Published in: Journal of lightwave technology Vol. 42; no. 10; pp. 3652 - 3660
• Main Authors: Kovaios, Stefanos, Pappas, Christos, Moralis-Pegios, Miltiadis, Tsakyridis, Apostolos, Giamougiannis, George, Kirtas, Manos, Van Kerrebrouck, Joris, Coudyzer, Gertjan, Yin, Xin, Passalis, Nikolaos, Tefas, Anastasios, Pleros, Nikos
• Format: Journal Article
• Language: English
• Published: New York IEEE 15.05.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Adaptive optics; Artificial neural networks; Integrated circuits; Machine learning; Neural networks; Neurons; Noise aware training; nonlinear activation function; Nonlinear optics; Optical communication; optical neural networks; opto-electronic activation function; Optoelectronic devices; Performance evaluation; Photonics; Training; Wavelength division multiplexing

We demonstrate an integrated opto-electronic (ΟΕ) device that can be programmed to provide a set of nonlinear activation functions (AFs) and present its operation within programmable tanh- and ELU-based photonic neurons at line rates up to 10 GBd. The OE activation module provides a set of well-know...