Udvidet returret til d. 31. januar 2024

Automated Deep Learning - Xuanyi Dong - Bog

- Neural Architecture Search Is Not the End

Bag om Automated Deep Learning

Deep learning (DL) has proven to be a highly effective approach for developing models in diverse contexts, including visual perception, speech recognition, and machine translation. Automated deep learning (AutoDL) endeavors to minimize the need for human involvement and is best known for its achievements in neural architecture search (NAS). In this monograph, the authors examine research efforts into automation across the entirety of an archetypal DL workflow. In so doing, they propose a comprehensive set of ten criteria by which to assess existing work in both individual publications and broader research areas, namely novelty, solution quality, efficiency, stability, interpretability, reproducibility, engineering quality, scalability, generalizability, and eco-friendliness. Aimed at students and researchers, this monograph provides an evaluative overview of AutoDL in the early 2020s, identifying where future opportunities for progress may exist.

Vis mere
  • Sprog:
  • Engelsk
  • ISBN:
  • 9781638283188
  • Indbinding:
  • Paperback
  • Udgivet:
  • 27. februar 2024
  • Størrelse:
  • 156x234x9 mm.
  • Vægt:
  • 245 g.
  • 2-3 uger.
  • 20. november 2024
På lager

Normalpris

  • BLACK NOVEMBER

Medlemspris

Prøv i 30 dage for 45 kr.
Herefter fra 79 kr./md. Ingen binding.

Beskrivelse af Automated Deep Learning

Deep learning (DL) has proven to be a highly effective approach for developing models in diverse contexts, including visual perception, speech recognition, and machine translation. Automated deep learning (AutoDL) endeavors to minimize the need for human involvement and is best known for its achievements in neural architecture search (NAS). In this monograph, the authors examine research efforts into automation across the entirety of an archetypal DL workflow. In so doing, they propose a comprehensive set of ten criteria by which to assess existing work in both individual publications and broader research areas, namely novelty, solution quality, efficiency, stability, interpretability, reproducibility, engineering quality, scalability, generalizability, and eco-friendliness. Aimed at students and researchers, this monograph provides an evaluative overview of AutoDL in the early 2020s, identifying where future opportunities for progress may exist.

Brugerbedømmelser af Automated Deep Learning



Find lignende bøger
Bogen Automated Deep Learning findes i følgende kategorier:

Gør som tusindvis af andre bogelskere

Tilmeld dig nyhedsbrevet og få gode tilbud og inspiration til din næste læsning.