A HIGH-PERFORMANCE CLOUD RESOURCE FOR COMPUTATIONAL MODELLING

Grant number: LE170100200 | Funding period: 2017 - 2017

Completed

Abstract

This project aims to build a relatively low-cost graphical-processing-unit-based cloud-accessible facility. Much current cutting-edge research is based on intensive computational models and simulations, which are used to deepen our understanding and predict real-world phenomena. This facility will provide a specialised computational platform for high-fidelity predictive models and simulations. It will underpin research in critical fields of science and engineering and be used by researchers from across Australia. This facility's computational capabilities are expected to complement other national computing resources, keep Australia globally competitive, and enhance research in fields includi..

View full description

Related publications (6)

Scholarly works icon

Towards Fair and Privacy-Preserving Federated Deep Models

L Lyu, J Yu, K Nandakumar, Y Li, X Ma, J Jin, H Yu, KS Ng

2020-11-01

The current standalone deep learning framework tends to result in overfitting and low utility. This problem can be addressed by ei..

Scholarly works icon

Simulations of compressibility effects in centrifugal buoyancy-induced flow in a closed rotating cavity

D Saini, RD Sandberg

2020-10-01

In this study, we investigate centrifugal buoyancy-induced flow by conducting numerical experiments for Rayleigh numbers in the ra..

Scholarly works icon

Learning Non-Unique Segmentation with Reward-Penalty Dice Loss

Jiabo He, Sarah Erfani, Sudanthi Wijewickrema, Stephen O'Leary, Kotagiri Ramamohanarao

2020-07-01

Semantic segmentation is one of the key problems in the field of computer vision, as it enables computer image understanding. Howe..

Scholarly works icon

Towards deep learning for connectome mapping: A block decomposition framework

Tabinda Sarwar, Caio Seguin, Kotagiri Ramamohanarao, Andrew Zalesky

2020-05-15

We propose a new framework to map structural connectomes using deep learning and diffusion MRI. We show that our framework not onl..

Scholarly works icon

Forcing frequency effects on turbulence dynamics in pulsatile pipe flow

Z Cheng, TO Jelly, SJ Illingworth, I Marusic, ASH Ooi

2020-04-01

The turbulence dynamics of pulsatile pipe flow are investigated using direct numerical simulation (DNS) at a mean friction Reynold..

Scholarly works icon

Improving MMD-GaN training with repulsive loss function

W Wang, Y Sun, S Halgamuge

2019-01-01

Generative adversarial nets (GANs) are widely used to learn the data sampling process and their performance may heavily depend on ..