Neural Architecture Search: Automating the Design of Deep Networks

Authors

  • Ali Asghar Associate Professor, Department of Computer Science, University of Lahore, Pakistan
  • Fatima Khan Assistant Professor, Department of Computer Engineering, National University of Sciences and Technology (NUST), Pakistan.
  • Imran Hussain Lecturer, Department of Artificial Intelligence, University of Karachi, Pakistan imran.

DOI:

https://doi.org/10.66421/int.j.datasci.intell.syst20

Keywords:

Neural Architecture Search, Deep Learning, Automation, Machine Learning, Search Algorithms, Reinforcement Learning, Evolutionary Algorithms, Model Optimization

Abstract

Neural Architecture Search (NAS) is an emerging area of research that focuses on automating the design of deep neural networks (DNNs). With the increasing complexity and performance requirements of machine learning models, manually designing architectures is becoming infeasible. NAS offers a promising solution by automating this process, enabling the discovery of high-performance architectures tailored to specific tasks. This paper explores the fundamental concepts, methodologies, and applications of NAS, highlighting the state-of-the-art algorithms and challenges in the field. The paper also investigates the role of NAS in advancing AI technologies, its practical applications in various domains, and its future directions in terms of scalability, efficiency, and integration with other machine learning paradigms.

References

Xie, L., & Yuille, A. (2017). Genetic CNN. Proceedings of the IEEE International Conference on Computer Vision (ICCV).

Zoph, B., & Le, Q. V. (2017). Neural architecture search with reinforcement learning. Proceedings of the International Conference on Machine Learning (ICML).

Real, E., et al. (2017). Large-Scale Evolution of Image Classifiers. Proceedings of the 34th International Conference on Machine Learning (ICML).

Cai, H., et al. (2018). ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware. Proceedings of the International Conference on Learning Representations (ICLR).

Liu, H., et al. (2018). DARTS: Differentiable Architecture Search. Proceedings of the International Conference on Learning Representations (ICLR).

Bengio, Y. (2009). Learning Deep Architectures for AI. Foundations and Trends in Machine Learning.

He, K., et al. (2015). Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. Proceedings of the IEEE International Conference on Computer Vision (ICCV).

Le, Q. V., et al. (2011). Building High-level Features Using Large Scale Unsupervised Learning. Proceedings of the International Conference on Machine Learning (ICML).

Xie, L., et al. (2018). SNAS: Stochastic Neural Architecture Search. Proceedings of the International Conference on Learning Representations (ICLR).

Howard, A. G., et al. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Sandler, M., et al. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Ahmad, N. R. (2025). Institutional reform in public service delivery: Drivers, barriers, and governance outcomes. Journal of Humanities and Social Sciences. https://doi.org/10.52152/jhs8rn12

Irk, E. (2026). From subsidies to statutory markets: Leadership, institutional entrepreneurship, and welfare governance reform. https://doi.org/10.52152/s59sjh53

Ahmad, N. R. (2025). Leadership styles in the 21st century: A comparative analysis of transformational and transactional leadership. Journal for Social Science Archives, 3(1), 576–587. https://doi.org/10.59075/jssa.v3i1.142

Ahmad, N. R. (2025). Corporate social responsibility in the digital age: Navigating ethical marketing and consumer expectations. Research Journal of Psychology, 3(1), 287–297. https://doi.org/10.59075/rjs.v3i1.66

Downloads

Published

2025-12-20