21–26 Jun 2026
U. Ottawa - Learning Crossroads (CRX) Building
America/Toronto timezone
Welcome to the 2026 CAP Congress Program website! / Bienvenue au siteweb du programme du Congrès de l'ACP 2026!

Active deep learning methods for regression

23 Jun 2026, 18:00
1h 30m
U. Ottawa - Learning Crossroads (CRX) Building

U. Ottawa - Learning Crossroads (CRX) Building

100 Louis-Pasteur Private, Ottawa, ON K1N 9N3
Poster Competition (Graduate Student) / Compétition affiches (Étudiant(e) 2e ou 3e cycle) Theoretical Physics / Physique théorique (DTP-DPT) DTP Poster Session & Student Poster Competition | Session d'affiches DPT et concours d'affiches étudiantes

Speaker

Kieran Watts (University of Ottawa)

Description

Active learning (AL) is under-researched for regression problems, with a majority of publications focusing on classification tasks. There is also a need for research concerning AL methods for deep learning. These methods are often approximations by necessity, as AL requires the models to not only predict current performance, but also changes in future performance. Deep learning methods do not directly provide this information.

   We investigate recent methods of AL data selection for regression including variance-based query-by-committee, Fisher information matrices, and feature-based largest cluster maximum distance selection. Within the query-by-committee methods, we compare two dropout pseudo-ensemble committee frameworks as well as a true ensemble setup. We test these methods for synthetic regression datasets that increase in complexity to recommend best use cases. We also use our findings of the methods' relative strengths and weaknesses to determine an optimal method for a high-dimensional nanophotonics inverse design project.
Keyword-1 Machine Learning
Keyword-2 AI for photonics
Keyword-3 Active learning

Author

Kieran Watts (University of Ottawa)

Co-authors

Dr Colin Bellinger (University of Ottawa) Lora Ramunno (University of Ottawa)

Presentation materials

There are no materials yet.