Automated Deep Learning : Neural Architecture Search Is Not the End

Xuanyi Dong

ISBN 10: 1638283184 / ISBN 13: 9781638283188

Published by Now Publishers Inc, 2024

About this Item

nach der Bestellung gedruckt Neuware - Printed after ordering - 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.

Seller Inventory # 9781638283188

Bibliographic Details

• Title: Automated Deep Learning : Neural Architecture Search Is Not the End
• Publisher: Now Publishers Inc
• Publication Date: 2024
• Language: English
• ISBN 10: 1638283184
• ISBN 13: 9781638283188
• Binding: Taschenbuch
• Condition: Neu

About this title

Synopsis

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.