Optical reservoir computing: prospects of using sub-10 picosecond lasers

Burlacu Alexandru

Articolul precedent

Articolul urmator

978

Ultima descărcare din IBN:
2023-04-10 15:45

SM ISO690:2012

BURLACU, Alexandru. Optical reservoir computing: prospects of using sub-10 picosecond lasers. In: Conferinţa tehnico-ştiinţifică a studenţilor, masteranzilor şi doctoranzilor, 1-3 aprilie 2020, Chișinău. Chișinău, Republica Moldova: 2020, Vol.1, pp. 262-264. ISBN 978-9975-45-633-3 (Vol. I).

EXPORT metadate:
Google Scholar
Crossref
CERIF

DataCite
Dublin Core

Conferinţa tehnico-ştiinţifică a studenţilor, masteranzilor şi doctoranzilor
Vol.1, 2020

Conferința "Conferinţa tehnico-ştiinţifică a studenţilor, masteranzilor şi doctoranzilor"
Chișinău, Moldova, 1-3 aprilie 2020

Optical reservoir computing: prospects of using sub-10 picosecond lasers

Pag. 262-264

Burlacu Alexandru

Technical University of Moldova

Disponibil în IBN: 22 iunie 2020

Descarcă PDF

Rezumat

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.

Cuvinte-cheie
reservoir computing, machine learning, optical computing, InGaN lasers

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance' xmlns='http://datacite.org/schema/kernel-3' xsi:schemaLocation='http://datacite.org/schema/kernel-3 http://schema.datacite.org/meta/kernel-3/metadata.xsd'>
<creators>
<creator>
<creatorName>Burlacu, A.I.</creatorName>
<affiliation>Universitatea Tehnică a Moldovei, Moldova, Republica</affiliation>
</creator>
</creators>
<titles>
<title xml:lang='en'>Optical reservoir computing: prospects of using sub-10 picosecond lasers</title>
</titles>
<publisher>Instrumentul Bibliometric National</publisher>
<publicationYear>2020</publicationYear>
<relatedIdentifier relatedIdentifierType='ISBN' relationType='IsPartOf'>978-9975-45-632-6</relatedIdentifier>
<subjects>
<subject>reservoir computing</subject>
<subject>machine learning</subject>
<subject>optical computing</subject>
<subject>InGaN lasers</subject>
</subjects>
<dates>
<date dateType='Issued'>2020</date>
</dates>
<resourceType resourceTypeGeneral='Text'>Conference Paper</resourceType>
<descriptions>
<description xml:lang='en' descriptionType='Abstract'><p>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.</p></description>
</descriptions>
<formats>
<format>application/pdf</format>
</formats>
</resource>