Please use this identifier to cite or link to this item: http://cris.utm.md/handle/5014/558
Title: Optical reservoir computing: prospects of using sub-10 picosecond lasers
Authors: BURLACU, Alexandru 
Keywords: reservoir computing;machine learning;optical computing;InGaN lasers
Issue Date: 2020
Source: BURLACU, Alexandru. Optical reservoir computing: prospects of using sub-10 picosecond lasers. In: Conferinţa tehnico-ştiinţifică a studenţilor, masteranzilor şi doctoranzilor. Volumul I, 1-3 aprilie 2020, Chișinău. Chișinău, Republica Moldova: 2020, pp. 262-264. ISBN 978-9975-45-632-6.
Project: 20.80009.5007.08. Studiul structurilor optoelectronice şi a dispozitivelor termoelectrice cu eficienţă înaltă 
Conference: Conferinţa tehnico-ştiinţifică a studenţilor, masteranzilor şi doctoranzilor 2020
Abstract: 
Training neural networks is hard. The industry is approaching the limits of siliconbased computing, both in terms of transistor size and chip dimensions. There are already examples of technologies that allow computations without using silicon. A paradigm for machine learning that could have enough representational power also exists. It is Reservoir Computing, which is also quite amenable for adaptation on non-silicon-based computing devices. In this work, I propose a specific type of laser-based reservoir computing scheme that builds on, and should improve, the existing solutions.
URI: https://ibn.idsi.md/ro/vizualizare_articol/106402
http://cris.utm.md/handle/5014/558
ISBN: 978-9975-45-632-6
Appears in Collections:Conference Abstracts

Files in This Item:
File Description SizeFormat
262-264_4.pdf217.5 kBAdobe PDFView/Open
Show full item record

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.