To access this element change to forms mode OFF
Grant Award View - GA350759-V1
Approximation theory of structured neural networks
GA ID:
GA350759-V1
Agency:
Australian Research Council
Approval Date:
12-Dec-2023
Variation Publish Date:
28-Feb-2024
Variation Date:
1-Aug-2024
Category:
Humanities, Arts and Social Sciences (HASS) Research
Grant Term:
1-Aug-2024 to 31-Jul-2027
Value (AUD):
$402,491.00
(GST inclusive where applicable)
Varies:
GA350759
- Approximation theory of structured neural networks
One-off/Ad hoc:
No
Aggregate Grant Award:
No
PBS Program Name:
ARC 23/24 Discovery
Grant Program:
Discovery Projects
Grant Activity:
Approximation theory of structured neural networks
Purpose:
Mathematical theory for deep learning has been desired due to the power applications of deep neural networks to deal with big data in various practical domains. The main difficulty lies in the structures and architectures imposed to networks designed for specific learning tasks. Neither the classical approximation theory nor the recent one for depths of ReLU neural networks can be applied due to the structures imposed for processing large dimensional data such as natural images of tens of thousands of dimensions. This project aims at an approximation theory for structured neural networks. We plan to establish mathematical theories for deconvolution with deep convolutional neural networks, operator learning, and spectral graph networks.
GO ID:
GO Title:
Discovery Projects for funding commencing in 2024
Internal Reference ID:
DP24 Round 1
Selection Process:
Targeted or Restricted Competitive
Confidentiality - Contract:
No
Confidentiality - Outputs:
No
Grant Recipient Details
Recipient Name:
The University of Sydney
Recipient ABN:
15 211 513 464
Grant Recipient Location
Suburb:
FOREST LODGE
Town/City:
FOREST LODGE
Postcode:
2037
State/Territory:
NSW
Country:
AUSTRALIA
Grant Delivery Location
State/Territory:
NSW
Postcode:
2037
Country:
AUSTRALIA