Translator Disclaimer
Poster + Presentation + Paper
5 March 2021 Image classification using delay-based optoelectronic reservoir computing
Author Affiliations +
Conference Poster
Abstract
Reservoir computing has emerged as a lightweight, high-speed machine learning paradigm. We introduce a new optoelectronic reservoir computer for image recognition, in which input data is first pre-processed offline using two convolutional neural network layers with randomly initialized weights, generating a series of random feature maps. These random feature maps are then multiplied by a random mask matrix to generate input nodes, which are then passed to the reservoir computer. Using the MNIST dataset in simulation, we achieve performance in line with state-of-the-art convolutional neural networks (1% error), while potentially offering order-of-magnitude improvement in training speeds.
Conference Presentation
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Philip Jacobson, Mizuki Shirao, Kerry Yu, Guan-Lin Su, and Ming C. Wu "Image classification using delay-based optoelectronic reservoir computing", Proc. SPIE 11703, AI and Optical Data Sciences II, 117031O (5 March 2021); https://doi.org/10.1117/12.2578062
PROCEEDINGS
7 PAGES + POSTER + PRESENTATION

SHARE
Advertisement
Advertisement
Back to Top