Automated Deep Learning
Neural Architecture Search Is Not the End
Seiten
2024
now publishers Inc (Verlag)
978-1-63828-318-8 (ISBN)
now publishers Inc (Verlag)
978-1-63828-318-8 (ISBN)
Automated deep learning (AutoDL) endeavours to minimize the need for human involvement and is best known for its achievements in neural architecture search (NAS). 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.
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) endeavours 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.
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) endeavours 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.
1. Introduction
2. AutoDL: An Overview
3. Automated Problem Formulation
4. Automated Data Engineering
5. Neural Architecture Search
6. Hyperparameter Optimization
7. Automated Deployment
8. Automated Maintenance
9. Critical Discussion and Future Directions
10. Conclusions
Acknowledgments
References
Erscheinungsdatum | 05.03.2024 |
---|---|
Reihe/Serie | Foundations and Trends® in Machine Learning |
Verlagsort | Hanover |
Sprache | englisch |
Maße | 156 x 234 mm |
Gewicht | 243 g |
Themenwelt | Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik |
ISBN-10 | 1-63828-318-4 / 1638283184 |
ISBN-13 | 978-1-63828-318-8 / 9781638283188 |
Zustand | Neuware |
Haben Sie eine Frage zum Produkt? |
Mehr entdecken
aus dem Bereich
aus dem Bereich
was sie kann & was uns erwartet
Buch | Softcover (2023)
C.H.Beck (Verlag)
18,00 €
von absurd bis tödlich: Die Tücken der künstlichen Intelligenz
Buch | Softcover (2023)
Heyne (Verlag)
20,00 €
dem Menschen überlegen – wie KI uns rettet und bedroht
Buch | Hardcover (2023)
Droemer (Verlag)
24,00 €