Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Canada Research Chairs

University of Toronto

$120,000.00

Generative Modeling

FY 2019-20

Summary
Automatic model-building systems will become more powerful as they explore larger model classes. However, the current limiting factor is our ability to do inference in these models - to efficiently compute what the data imply about the hidden structure.We propose to develop model classes with arbitrarily-complex latent structures, and corresponding fast inference methods. This approach combines the interpretability of structured models, such as clustering, time-series, or topic models, with the flexibility of neural networks. This combination avoids the rigid modeling assumptions usually required for efficient inference, and addresses the uninterperetability of neural networks.
Program
Canada Research Chairs
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
1000231621-2016
Name nom
Duvenaud, David
Department département
Computer Science/Arts & Science
Organization id
31
Institution établissement
University of Toronto
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2019
Competition year année de concours
2016
Award amount
120000
Program id
CRC
Program name en
Canada Research Chairs
Program name fr
Chaires de recherche du Canada
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
9998
Committee name en
Canada Research Chair Selection Committee
Committee name fr
Comité de sélection des Chaires de recherche du Canada
Area of application code
9999
Area of application group en
Not available
Area of application group fr
Non disponible
Area of application en
Not available
Area of application fr
Non disponible
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)
Installment
NA
Partie
0
Nb partie
NA
Application title
Generative Modeling
Keyword
NSERC
Application summary
Automatic model-building systems will become more powerful as they explore larger model classes. However, the current limiting factor is our ability to do inference in these models - to efficiently compute what the data imply about the hidden structure.We propose to develop model classes with arbitrarily-complex latent structures, and corresponding fast inference methods. This approach combines the interpretability of structured models, such as clustering, time-series, or topic models, with the flexibility of neural networks. This combination avoids the rigid modeling assumptions usually required for efficient inference, and addresses the uninterperetability of neural networks.