How photonic reservoirs improve the performance of deep neural networks

Research output: Chapter in Book/Report/Conference proceedingConference paper

Abstract

Large deep neural networks (DNNs) have been successfully used for solving complex problems. However, they are often very energy-intensive and time-consuming to train. In this work, we propose to use a photonic reservoir to preprocess the input instead of directly injecting it into the DNN. The advantage of using such a photonic reservoir is that it consists of a network of many randomly connected nodes which do not need to be trained. We numerically show that using such a photonic reservoir as preprocessor results in an improved performance for deep neural networks on a time-series prediction task. We observe that using a stand-alone DNN results in a high test error. If we combine this DNN with a photonic reservoir as preprocessor, we achieve a better performance, shown by a lower test error. Furthermore, it is able to outperform the long short-term memory (LSTM) network with a lower test error and lower total training time. Photonic reservoirs are ideal candidates as physical preprocessors to deep neural networks due to their fast computation times and low-energy consumption.
Original languageEnglish
Title of host publicationProceedings of the 27th Annual Symposium of the IEEE Photonics Society Benelux Chapter
PublisherIEEE Photonics Benelux Chapter
Pages1-4
Number of pages4
Publication statusPublished - 24 Nov 2023
EventIEEE Photonics Benelux Chapter Annual Symposium 2023 - Oude Abdij, Drongen, Belgium
Duration: 23 Nov 202324 Nov 2023
https://www.aanmelder.nl/ieee-ps-benelux-2023

Conference

ConferenceIEEE Photonics Benelux Chapter Annual Symposium 2023
Country/TerritoryBelgium
CityDrongen
Period23/11/2324/11/23
Internet address

Fingerprint

Dive into the research topics of 'How photonic reservoirs improve the performance of deep neural networks'. Together they form a unique fingerprint.

Cite this