Discovery Projects - Grant ID: DP240101919

Funding Activity

Website
http://dataportal.arc.gov.au/NCGP/Web/Grant/Grant/DP240101919

Funding Status
Active

Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the .

Funded Activity Summary

Approximation theory of structured neural networks . 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.

Funded Activity Details

Start Date: 01-08-2024

End Date: 31-07-2027

Funding Scheme: Discovery Projects

Funding Amount: $402,491.00

Funder: Australian Research Council

Research Topics

ANZSRC Field of Research (FoR)

Numerical and computational mathematics not elsewhere classified | Approximation theory and asymptotic methods | Numerical and computational mathematics

ANZSRC Socio-Economic Objective (SEO)

Other Keywords

Approximation theory and asymptotic methods | Expanding Knowledge In the Mathematical Sciences | Numerical and computational mathematics | Numerical and computational mathematics not elsewhere classified

Related Links