Work

Photorefractive Integrated Photonics for Analog Signal Processing in AI

Year: 2024

Type: article

Abstract: The computational cost of AI could be alleviated by accelerating the synaptic transfer calculations in artificial neural networks with an analog crossbar array processor. In this work, we present the core building blocks of an all-optical integrated photorefractive crossbar array for artificial neural network training by demonstrating photorefractive synapses in an integrated 2-D beam interaction network. We show that the photorefractive quality of the circuits resembles that of the bulk GaAs crystal that they were fabricated from. Then, this work experimentally validates the integrated photorefractive crossbar array design and constitutes a framework for engineering photorefractive integrated photonics.

Source: IEEE Journal of Selected Topics in Quantum Electronics

DOI: 10.1109/jstqe.2024.3519983

Authors: Elger A. Vlieg, Roger Dangel, Bert J. Offrein, Folkert Horst

Institution: IBM Research - Zurich

Language: English

Topic: Neural Networks and Reservoir Computing

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $2,495

OpenAlex ID: W4405517415

FWCI: 0.295

Cites: 36

Cited by: 2

Related to: 10