Alexandre HEUILLET defends his doctoral thesis on Monday December 4, 2023 at 3:30 p.m. in Amphitheater Bx30 on the Pelvoux site of the University of Évry.
A broadcast via Zoom is also available: https://universite-paris-saclay-fr.zoom.us/j/96288613809?pwd=Uzd5OXJvMHVLdWhWaERtbk9qeXVIdz09
Title : Exploring Differentiable Neural Architecture Search for Deep Neural Network Design
Abstract :
Artificial Intelligence (AI) has gained significant popularity in recent years, primarily due to its successful applications in various domains, including textual data analysis, computer vision, and audio processing. The resurgence of deep learning techniques has played a central role in this success. The groundbreaking paper by Krizhevsky et al., AlexNet, narrowed the gap between human and machine performance in image classification tasks. Subsequent papers such as Xception and ResNet have further solidified deep learning as a leading technique, opening new horizons for the AI community. The success of deep learning lies in its architecture, which is manually designed with expert knowledge and empirical validation. However, these architectures lack the certainty of an optimal solution. To address this issue, recent papers introduced the concept of Neural Architecture Search (NAS), enabling the learning of deep architectures. However, most initial approaches focused on large architectures with specific targets (e.g., supervised learning) and relied on computationally expensive optimization techniques such as reinforcement learning and evolutionary algorithms. In this thesis, we further investigate this idea by exploring automatic deep architecture design, with a particular emphasis on differentiable NAS (DNAS), which represents the current trend in NAS due to its computational efficiency. While our primary focus is on Convolutional Neural Networks (CNNs), we also explore Vision Transformers (ViTs) with the goal of designing cost-effective architectures suitable for real-time applications.
Composition of the doctoral thesis jury
| Jury member | Title | Affiliation | Function in the jury |
|---|---|---|---|
| Hichem ARIOUI | Assistant professor | Université Paris-Saclay, Univ. Évry | Thesis co-supervisor |
| Florence D’ALCHÉ-BUC | Full professor | Télécom Paris, Institut Polytechnique de Paris | Rapporteure |
| Isabelle GUYON | Full professor | Université Paris-Saclay, Google Brain | Invited member |
| Blaise HANCZAR | Full professor | Université Paris-Saclay, Univ. Évry | Examinateur |
| David PICARD | Full professor | École des Ponts ParisTech, CNRS, Université Gustave Eiffel | Examinateur |
| Raúl SANTOS-RODRIGUEZ | Professor | Université de Bristol | Rapporteur |
| Hedi TABIA | Full professor | Université Paris-Saclay (Univ. Évry) | Thesis supervisor |
| Kamal YOUCEF-TOUMI | Professor | Massachusetts Institute of Technology (Etats-Unis) | Invited member |
- Date: Monday 04/12/2023, 3:30pm
- Location: Site Pelvoux, University of Évry, Amphitheater Bx30
Webcast via Zoom https://universite-paris-saclay-fr.zoom.us/j/96288613809?pwd=Uzd5OXJvMHVLdWhWaERtbk9qeXVIdz09 - PhD student : Alexandre HEUILLET, IBISC IRA2 team
- Thesis supervisors: Hedi TABIA (Full professor Univ. Évry, IBISC IRA2 team), Hicham ARIOUI (Assistant professor, IBISC SIAM team)
