SEMINARS
- Cryptographic protocols for privacy-preserving data pipelines
- Alex Davidson (FCT NOVA - NOVA LINCS)
- 15/03/2023 14:00, Host: Computer Systems
- World Logic Day | Logic-based Explanations for Neural Networks
- João Leite (Head of the Department of Computer Science, NOVA School of Science and Technology)
- 08/03/2023 14:00, Host: Inteligent Systems
- Gaussian Processes for Shape Modelling: a Probabilistic Registration Approach
- Filipa Valdeira (NOVA LINCS)
- 01/03/2023 14:00, Host: Inteligent Systems
- World Logic Day | Logic, Computation, and Programming Languages
- Luís Caires (Director of NOVA LINCS, NOVA School of Science and Technology)
- 22/02/2023 14:00, Host: Software Systems
- Cart-ology: Intercepting Targeted Advertising via Ad Network Identity Entanglement
- Damon McCoy (Tandon School of Engineering, New York University)
- 15/02/2023 14:00, Host: Computer Systems
- Open-Task Multimodal Conversational AI
- João Magalhães
- 30/11/2022 14:00, Host: Multimodal Systems
- Breaking MPC implementations through compression
- João Resende (DI FCT NOVA)
- 23/11/2022 14:00, Host: Computer Systems
- Gradual Verification: Assuring Software Incrementally
- Jonathan Aldrich (Carnegie Mellon University)
- 11/11/2022 11:00, Host: Software Systems
- Automata for choreographies
- Emilio Tuosto (Gran Sasso Science Institute (GSSI), Italy)
- 27/07/2022 14:00, Host: Software Systems
- Graph Data Processing Techniques
- Stefania Dumbrava (École Nationale Supérieure d'Informatique pour l'Industrie et l'Entreprise (ENSIIE) & SAMOVAR research laboratory - Institute Polytechnique de Paris)
- 20/07/2022 14:00, Host: Software Systems
- The Quest for Bullet-proof Software Systems.
- Mário Pereira
- 13/07/2022 14:00, Host: Software Systems
- A Novel One-shot Neural Network Architecture Search via Regression
- Neural architecture search (NAS) has become a central theme for the recent research trend on autoAI, i.e., how to find an effective deep neural network (DNN) by automatically searching a large neural architecture design space. One major drawback is, however, the large computation time used to search a high-quality neural architecture. In this talk, we will discuss one of our recent works in NAS where we show a simple intuition that was surprisingly effective in guiding us to design a fast NAS, which has achieved new state-of-the-arts results in both image and natural language related tasks but with orders of magnitude performance speedup. We call this technique as Generic Neural Architecture Search via Regression (GenNAS). If time permits, I will also discuss how we ended up doing NAS research in this space, and what new theoretical research topics may be needed in order to better understand GenNAS for its generalization capabilities.
- Jinjun Xiong (University at Buffalo)
- 27/06/2022 14:00, Host: Inteligent Systems
Seminar
Seminar
Seminar
Seminar
Seminar
Seminar
Seminar
Seminar
Seminar
Seminar
Seminar
Seminar