Grant: Alliance Grants
The University of Western Ontario
$25,000.00
Fair Lifelong Learning in Non-Stationary Environments for Medical Imaging
EF 2024-25
Résumé
Lifelong learning (LL) considers an intelligent agent that can continually accumulate and transfer its knowledge to adapt to new tasks, which is a fundamental step towards artificial intelligence. Despite recent advances in LL, which have primarily focused on overcoming catastrophic forgetting, there are still bottleneck issues, especially when deploying LL systems for real-world applications, such as medical imaging. In particular, (A) how to guarantee fairness without losing the prediction performance; and (B) how to adapt to the non-stationary distribution of tasks. To address these issues, this project aims to design LL algorithms that enable accurate and fair predictions with theoretical justifications, and adapt to changing environments without catastrophic forgetting. We will also apply our techniques in medical image analysis, yielding the first principled and practical LL systems that transform the landscape of this research with new standards (e.g., continually processing medical images in a fair and adaptive manner).
Programme
Alliance Grants
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
592874-2024
Name nom
Wang, Boyu B
Department département
Computer Science
Organization id
36
Institution établissement
The University of Western Ontario
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
25000
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
1211
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Medical and health sciences
Area of application fr
Sciences médicales et de la santé
Research subject code
2800
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Artificial intelligence (computer vision, use2603)
Research subject fr
Intelligence artificielle (vision artificielle, utiliser 2603)
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Fair Lifelong Learning in Non-Stationary Environments for Medical Imaging
Keywords
fairness in machine learning; lifelong learning; machine learning; medical image analysis; transfer learning
Application summary
Lifelong learning (LL) considers an intelligent agent that can continually accumulate and transfer its knowledge to adapt to new tasks, which is a fundamental step towards artificial intelligence. Despite recent advances in LL, which have primarily focused on overcoming catastrophic forgetting, there are still bottleneck issues, especially when deploying LL systems for real-world applications, such as medical imaging. In particular, (A) how to guarantee fairness without losing the prediction performance; and (B) how to adapt to the non-stationary distribution of tasks. To address these issues, this project aims to design LL algorithms that enable accurate and fair predictions with theoretical justifications, and adapt to changing environments without catastrophic forgetting. We will also apply our techniques in medical image analysis, yielding the first principled and practical LL systems that transform the landscape of this research with new standards (e.g., continually processing medical images in a fair and adaptive manner).