Journal article Open Access

Memory Optimization Techniques in Neural Networks: A Review

Pratheeksha P; Pranav B M; Azra Nasreen


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-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="URL">https://zenodo.org/record/5410409</identifier>
  <creators>
    <creator>
      <creatorName>Pratheeksha P</creatorName>
      <affiliation>Department of Computer Science, R. V College of Engineering, Bengaluru (Karnataka), India.</affiliation>
    </creator>
    <creator>
      <creatorName>Pranav B M</creatorName>
      <affiliation>Department of Computer Science, R. V College of Engineering, Bengaluru (Karnataka), India.</affiliation>
    </creator>
    <creator>
      <creatorName>Azra Nasreen</creatorName>
      <affiliation>Assistant Professor, Department of Computer Science, R. V College of Engineering, Bengaluru (Karnataka), India.</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Memory Optimization Techniques in Neural Networks: A Review</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2021</publicationYear>
  <subjects>
    <subject>Memory footprint reduction, Backpropagation  through time (BPTT), CNN, RNN.</subject>
    <subject subjectScheme="issn">2249-8958</subject>
    <subject subjectScheme="handle">100.1/ijeat.F29910810621</subject>
  </subjects>
  <contributors>
    <contributor contributorType="Sponsor">
      <contributorName>Blue Eyes Intelligence Engineering  and Sciences Publication (BEIESP)</contributorName>
      <affiliation>Publisher</affiliation>
    </contributor>
  </contributors>
  <dates>
    <date dateType="Issued">2021-08-30</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="JournalArticle"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/5410409</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="ISSN" relationType="IsCitedBy" resourceTypeGeneral="JournalArticle">2249-8958</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsIdenticalTo">10.35940/ijeat.F2991.0810621</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;Deep neural networks have been continuously evolving towards larger and more complex models to solve challenging problems in the field of AI. The primary bottleneck that restricts new network architectures is memory consumption. Running or training DNNs heavily relies on the hardware (CPUs, GPUs, or FPGA) which are either inadequate in terms of memory or hard-to-extend. This would further make it difficult to scale. In this paper, we review some of the latest memory footprint reduction techniques which would enable faster low model complexity. Additionally, it improves accuracy by increasing the batch size and developing wider and deeper neural networks with the same set of hardware resources. The paper emphasizes on memory optimization methods specific to CNN and RNN training.&lt;/p&gt;</description>
  </descriptions>
</resource>
20
20
views
downloads
Views 20
Downloads 20
Data volume 4.8 MB
Unique views 19
Unique downloads 20

Share

Cite as