[TuP-G] Poster Session 1

[TuP-G-5] Device-Informed Training Strategy for Low-Precision Photonic Neural Networks

Vikas Kumar Keshari¹, Dhrutisundar Sahoo¹, Abhishek Kumar Anand¹, ○Lorenzo De Marinis², Emilio Paolini², Jimson Mathew¹, Nicola Andriolli³, Giampiero Contestabile², Sumanta Gupta¹ (1. Indian Institute of Technology Patna, India (India), 2. Scuola Superiore Sant’Anna, Pisa, Italy (Italy), 3. University of Pisa, Pisa, Italy (Italy))

Keywords:

Photonics for neuromorphic computing and deep learning,Photonics in neuromorphic computing and machine learning devices

This paper compares three training strategies for low-precision photonic neural networks. The efficacy of the schemes is tested through circuital simulations on the photonic electronic multiply-accumulate neuron (PEMAN) architecture with three different datasets.