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. However, the end-to-end process for applying DL is not trivial. It requires grappling with problem formulation and context understanding, data engineering, model development, deployment, continuous monitoring and maintenance, and so on. Moreover, each of these steps typically relies heavily on humans, in terms of both knowledge and interactions, which impedes the further advancement and democratization of DL. Consequently, in response to these issues, a new field has emerged over the last few years: automated deep learning (AutoDL). This endeavor seeks to minimize the need for human involvement and is best known for its achievements in neural architecture search (NAS), a topic that has been the focus of several surveys. That stated, NAS is not the be-all and end-all of AutoDL. Accordingly, this review adopts an overarching perspective, examining research efforts into automation across the entirety of an archetypal DL workflow. In so doing, this work also proposes a comprehensive set of ten criteria by which to assess existing work in both individual publications and broader research areas. These criteria are: novelty, solution quality, efficiency, stability, interpretability, reproducibility, engineering quality, scalability, generalizability, and eco-friendliness. Thus, ultimately, this review provides an evaluative overview of AutoDL in the early 2020s, identifying where future opportunities for progress may exist.
Article navigation
27 February 2024
Research Article|
February 27 2024
Automated Deep Learning: Neural Architecture Search Is Not the End
Xuanyi Dong;
Xuanyi Dong
Complex Adaptive Systems Lab,
University of Technology Sydney
, Australia
and Brain Team, Google Research, USA
Search for other works by this author on:
David Jacob Kedziora;
David Jacob Kedziora
Complex Adaptive Systems Lab,
University of Technology Sydney
, Australia
Search for other works by this author on:
Katarzyna Musial;
Katarzyna Musial
Complex Adaptive Systems Lab,
University of Technology Sydney
, Australia
Search for other works by this author on:
Bogdan Gabrys
Bogdan Gabrys
Complex Adaptive Systems Lab,
University of Technology Sydney
, Australia
and Brain Team, Google Research, USA
Search for other works by this author on:
Online ISSN: 1935-8245
Print ISSN: 1935-8237
© 2024 X. Dong et al.
2024
X. Dong et al.
Licensed re-use rights only
Foundations and Trends in Machine Learning (2024) 17 (5): 767–920.
Citation
Dong X, Kedziora DJ, Musial K, Gabrys B (2024), "Automated Deep Learning: Neural Architecture Search Is Not the End". Foundations and Trends in Machine Learning, Vol. 17 No. 5 pp. 767–920, doi: https://doi.org/10.1561/2200000119
Download citation file:
New and popular articles
Suggested Reading
DRN-GAN: an integrated deep learning-based health degradation assessment model for naval propulsion system
Engineering Computations (April,2022)
Deep learning or interpolation for inverse modelling of heat and fluid flow problems?
International Journal of Numerical Methods for Heat & Fluid Flow (January,2021)
Related Chapters
Summary and practical next steps
Addressing Climate Risk in Coastal Urban Areas of East and Southeast Asia: Connecting Climate Science, Engineering and Finance
Chapter 3 An International Dimension: Aviation
Transport and Climate Change
Adaptation in Business Contexts: Working Triadic Relationships
Deep Knowledge of B2B Relationships Within and Across Borders
Recommended for you
These recommendations are informed by your reading behaviors and indicated interests.
