Journal article Open Access

Memory Optimization Techniques in Neural Networks: A Review

Pratheeksha P; Pranav B M; Azra Nasreen


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Memory footprint reduction, Backpropagation  through time (BPTT), CNN, RNN.</subfield>
  </datafield>
  <controlfield tag="005">20210904014840.0</controlfield>
  <controlfield tag="001">5410409</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Department of Computer Science, R. V College of Engineering, Bengaluru (Karnataka), India.</subfield>
    <subfield code="a">Pranav B M</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Assistant Professor, Department of Computer Science, R. V College of Engineering, Bengaluru (Karnataka), India.</subfield>
    <subfield code="a">Azra Nasreen</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Publisher</subfield>
    <subfield code="4">spn</subfield>
    <subfield code="a">Blue Eyes Intelligence Engineering  and Sciences Publication (BEIESP)</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">238425</subfield>
    <subfield code="z">md5:f3b5811d3d8d333a3e0edcf199ec3663</subfield>
    <subfield code="u">https://zenodo.org/record/5410409/files/F29910810621.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2021-08-30</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="o">oai:zenodo.org:5410409</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="4">
    <subfield code="c">44-48</subfield>
    <subfield code="n">6</subfield>
    <subfield code="p">International Journal of Engineering and Advanced Technology (IJEAT)</subfield>
    <subfield code="v">10</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Department of Computer Science, R. V College of Engineering, Bengaluru (Karnataka), India.</subfield>
    <subfield code="a">Pratheeksha P</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Memory Optimization Techniques in Neural Networks: A Review</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2=" ">
    <subfield code="a">ISSN</subfield>
    <subfield code="0">(issn)2249-8958</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2=" ">
    <subfield code="a">Retrieval Number</subfield>
    <subfield code="0">(handle)100.1/ijeat.F29910810621</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&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;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">issn</subfield>
    <subfield code="i">isCitedBy</subfield>
    <subfield code="a">2249-8958</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.35940/ijeat.F2991.0810621</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">article</subfield>
  </datafield>
</record>
20
20
views
downloads
Views 20
Downloads 20
Data volume 4.8 MB
Unique views 19
Unique downloads 20

Share

Cite as