Scaling on-chip photonic neural processors using arbitrarily programmable wave propagation

• Published in: arXiv.org
• Main Authors: Onodera, Tatsuhiro, Stein, Martin M, Ash, Benjamin A, Sohoni, Mandar M, Bosch, Melissa, Yanagimoto, Ryotatsu, Jankowski, Marc, McKenna, Timothy P, Wang, Tianyu, Shvets, Gennady, Shcherbakov, Maxim R, Wright, Logan G, McMahon, Peter L
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 27.02.2024
• Subjects: Classification; Continuous radiation; Handwriting; Microprocessors; Modulation; Neural networks; Optical communication; Photonics; Processors; Propagation; Refractivity; Substrates; Wave propagation; Waveguides

On-chip photonic processors for neural networks have potential benefits in both speed and energy efficiency but have not yet reached the scale at which they can outperform electronic processors. The dominant paradigm for designing on-chip photonics is to make networks of relatively bulky discrete co...