Optimizing Convolution Neural Nets with a Unified Transformation Approach.

The article explores how deep learning models have evolved from relying on hand-crafted operator libraries to utilizing compiler-based approaches for optimization, especially with the growing diversity of hardware platforms. It highlights the Apache TVM project, which allows machine learning enginee...

Descripción completa

Detalles Bibliográficos
Publicado en:Communications of the ACM Vol. 67; no. 10; pp. 91 - 92
Autor principal: Ceze, Luis
Formato: Opinion
Publicado: Association for Computing Machinery Oct2024
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=179943076&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 179943076
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        00010782
        ACM
      jtl: Communications of the ACM
      issn: 00010782
      maglogo: N
    pubinfo:
      dt: Oct2024
      vid: 67
      iid: 10
      pid: 68
      pub: Association for Computing Machinery
    artinfo:
      ui:
        179943076
        10.1145/3657630
      ppf: 91
      ppct: 1
      formats:
      tig:
        atl: Optimizing Convolution Neural Nets with a Unified Transformation Approach.
      aug:
        au: Ceze, Luis
        affil: University of Washington, Paul G. Allen School of Computer Science and Engineering, Seattle, WA, USA
      su:
        Deep learning
        Machine learning
        Computer architecture
        Mathematical optimization
        Computer input-output equipment
        Compilers (Computer programs)
      sug:
        subj:
          Deep learning
          Machine learning
          Computer architecture
          Mathematical optimization
          Computer input-output equipment
          Compilers (Computer programs)
      ab: The article explores how deep learning models have evolved from relying on hand-crafted operator libraries to utilizing compiler-based approaches for optimization, especially with the growing diversity of hardware platforms. It highlights the Apache TVM project, which allows machine learning engineers to compile models for specific hardware targets, optimizing performance without altering model accuracy. The article points to an accompanying paper that proposes a unified transformation approach that optimizes model architectures through program transformations, avoiding expensive retraining and achieving significant performance gains without compromising accuracy.
      pubtype: Periodical
      doctype: Opinion
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      dt:
        @attributes:
          year: 2024
    holdings:
      @attributes:
        islocal: N