To access this element change to forms mode OFF
Grant Award View - GA337651
Universal Model Selection Criteria for Scientific Machine Learning
GA ID:
GA337651
Agency:
Australian Research Council
Approval Date:
28-Sep-2023
Publish Date:
4-Oct-2023
Category:
Humanities, Arts and Social Sciences (HASS) Research
Grant Term:
1-Jan-2024 to 31-Dec-2026
Value (AUD):
$444,447.00
(GST inclusive where applicable)
One-off/Ad hoc:
No
Aggregate Grant Award:
No
PBS Program Name:
ARC 23/24 Discovery
Grant Program:
Discovery Early Career Researcher Award
Grant Activity:
Universal Model Selection Criteria for Scientific Machine Learning
Purpose:
This project aims to develop provably reliable universal model selection criteria to facilitate trustworthy scientific machine learning. Combining stochastic methods with an innovative geometric approach to basic statistical principles, this project expects to characterise, combine, and refine the most successful heuristics for designing and training huge models, such as deep neural networks, into a cohesive theoretical framework. The expected outcomes include a general toolkit for assisting neural network design at the forefront of scientific applications. This should significantly improve the quality of scientific predictions by facilitating confident adoption of deep learning methods into the pantheon of trustworthy modeling techniques.
GO ID:
GO Title:
Discovery Early Career Researcher Award for funding commencing in 2024
Internal Reference ID:
DE24 Round 1
Selection Process:
Targeted or Restricted Competitive
Confidentiality - Contract:
No
Confidentiality - Outputs:
No
Grant Recipient Details
Recipient Name:
The University of Melbourne
Recipient ABN:
84 002 705 224
Grant Recipient Location
Suburb:
UNIVERSITY OF MELBOURNE
Town/City:
UNIVERSITY OF MELBOURNE
Postcode:
3010
State/Territory:
VIC
Country:
AUSTRALIA
Grant Delivery Location
State/Territory:
VIC
Postcode:
3010
Country:
AUSTRALIA