Distributed Algorithms CDT
12 Apr 2019
Yes
-  

 

 

Funded by EPSRC, the Distributed Algorithms CDT offers studentships at the University of Liverpool with joint supervision from the Hartree Centre.

Yes

​​​​​​​​​

 

CDT Header.jpg

At the Hartree Centre, we apply transformative advanced computing, data analytics and AI technologies to industry-relevant challenges, and this is reflected in the six projects we're co-supervising with the University of Liverpool as part of the Distributed Algorithms CDT​

Through each of the​​ funded projects below, we hope to provide you with an exciting and engaging area of cutting-edge computational science to immerse yourself in, whilst also delivering essential training in sought-after technical skills that are valued by both science and industry, setting you up for future career success. ​


​​​​​Available Projects

​​​​Scalable, Model Agnostic GPU Framework for ​Bayesian Deep Learning and Bayesian Optimisation 

Supervisors: 

Dr. Edoardo Patelli | University of Liverpool

Dr. Jony Castagna | STFC Hartree Centre



​You will employ state of the art Bayesian Deep Learning algorithms and exploit sparse and large datasets to run on advanced accelerator GPU-based architectures. 

This project will equip you with invaluable skills to employ big data analytics methods, help you to acquire advanced programing skills in developing and applying Deep Learning methods to real-word industry problems and using modern GPU-based computer architectures.​

Track Before Detect Bayes

Supervisors: 

Dr. Angel Garcia-Fernandez | University of Liverpool

Prof. Vassil Alexandrov | STFC Hartree Centre



​Develop efficient and adaptive object tracking methods based on the Track Before Detect (TBD) concept, employing  modern Bayesian sampling methods to allow information to be collected from supplementary information sources. You will then run the resulting algorithms on a scalable computer architecture, thus allowing large numbers of objects to be tracked.

The successful student will acquire advanced programing skills in deploying modern Bayesian sampling methods for analysing complex sets of data in real time on modern parallel computer architectures.

​Coordination and Cooperation in Adversarial Engagements

Supervisors: 

Prof. Jason Ralph | University of Liverpool

Prof. Vassil Alexandrov | STFC Hartree Centre



You will develop methods to provide tactical guidance and decision making for future air defence systems. The aim will be to provide assistance to an operator that is robust, timely and that optimises the defensive response across all available assets; including platforms/vehicles, countermeasures, and interceptors.

The student will acquire skills of using advanced Data Analytics methods and approaches, how to combine multiple data streams and to perform advances computations in modelling such complex systems on advanced computer architectures.​

Fast Bayesian Deep Learning

Supervisors: 

Prof. SImon Maskell | University of Liverpool

Prof. Vassil Alexandrov | STFC Hartree Centre




​Exploit the inherent parallelism of Sequential Monte Carlo (SMC) sampler combined with parallel Deep Learning approaches to compute the many hypotheses that the data could imply to be true on advanced computer architectures -  including accelerator GPU based ones.

During this project, the student will acquire technical skills in implementing parallel stochastic methods and Deep Learning on advanced parallel computer architectures as well as efficiently analysing hypotheses.
 

Distributed Implementations of Machine-learned Defect Detection for Additive Manufacturing (AM)​ ​

Supervisors: 

Dr. Pete Green | Univeristy of Liverpool

Dr. Xiahuo Guo | STFC Hartree Centre




Aiming to vastly enhance production control in Additive Manufacturing, you will use advanced Machine Learning methods to exploit the vast amounts of process measurements that can be captured during an AM build, such as temperature, back-reflected light etc. You will then use this knowledge to develop process control strategies.

The successful student will develop essential skills in applying advanced Machine Learning methods for analysis of very large datasets, and learn how to run the corresponding parallel algorithms on advanced computer architectures.

Faster Uncertainty Quantification of Hydrocodes ​

Supervisors: 

Prof. Leszek Gasieniec | University of Liverpool

Dr. Luke Mason | STFC Hartree Centre




​Taking a specific hydrocode, you will examine how advanced statistical and computational approaches (in isolation and in combination) can be used to develop a single integrated approach to analysing and speeding up Uncertainty Quantification (UQ) on complex systems. The approach will be underpinned by a synergistic understanding of computer science and statistics.

The successful student will acquire skills to apply advanced UQ approaches to complex problems as well as how to efficiently implement them on advanced computer architectures.

View all available projects

Application deadline for all projects: 3​ May 2019​


​​​​​​​Meet the supervisors


Vassil AlexandrovCDT.jpg
Prof. Vassil Alexandrov

I've worked in high performance computing (HPC), data and computational science for a long time, with a fulfilling career spanning 18 years and 5 countries! I've also published over 130 papers in journals and at international conferences and workshops. I'm excited to be a supervisor so that I can pass on my knowledge and experience to the next generation of young people who will develop research projects in exciting areas of HPC and data science.

During my career, I have supervised 31 PhD students to successful completion of their PhD studies across a variety of computational themes and areas, and been a Programme Director of 3 MSc programmes. I am a member of the Editorial Board of the Journal of Computational Science (JOCS) and Editor of Mathematics and Computers in Simulation journal.

My long-term expertise in Monte Carlo means I am particularly interested in seeing how we can further speed up these simulations. Currently, mathematics-led innovation is clearly indispensable in advancing key scientific areas, as well as powering methods and algorithms enabling to discover global properties of data.


Dr. Xiaohu Guo 

I've been interested in science in my whole life, especially computational science, and can see that it is turning into more and more powerful tool for scientists to explore exciting new areas and unknowns. What excites me about computational science is the great sense of achievement I feel when the algorithms/methods that were turned into codes by my logic and own creativity can be used by every one! What I love about working here is bridging a gap between research academics and industrial applications.

I develop enabling technologies for a wide range of engineering and science applications. I was the lead developer of Incompressible Smoothed Particle Hydrodynamics (ISPH) software package ISPH3D which has been recognised the first open source ISPH software package in the world, which has wide application in the area of nuclear thermal hydraulics, offshore and marine energy industries, offshore oil and gas industries and coastal engineering consultancies involved in the design of coastal defences.


Xiaohu GuoCDT.jpg
​​Jony CastagnaCDT.jpg
Dr. Jony Castagna

I joined the Science and Technology Facilities Council (STFC) Hartree Centre in 2016 and since then I have enjoyed my work more and more. I am a computational scientist with a strong passion for high performance computing (HPC), usually oriented to the Simulation of Turbulent Flows using Computational Fluid Dynamics… But let me just say it: I love programming GPUs! CUDA is my favourite language, but I recently start to use OpenACC more due its portability to other platforms.  

Working with GPUs since 2010, how could I not end up in Deep Learning? This new fascinating world has recently captured me… and transformed me into an NVIDIA Ambassador here at STFC! So, while I enjoy running NVIDIA Deep Learning Institute courses ranging from CUDA to Deep Learning for Computer Vision, my main focus stays on applied HPC for scientific research, mainly using future computing systems like hybrid CPU-GPU architectures where integration between artificial intelligence (AI) and traditional HPC science is merged together.


Dr. Luke Mason 

I've worked in computational science for 15 years and started by developing control software for embedded and robotic systems before moving to high performance computing (HPC) 10 years ago. I have worked on a diverse range of HPC software over the years, from models of high velocity impact to porting weather and climate models to new computing architectures. I currently lead the High Performance Software Engineering Group at the Science and Technology Facilities Council (STFC) Hartree Centre. We specialise in code scalability and performance on HPC systems, as well as porting and optimisation for emerging technologies and novel architectures.

I enjoy working alongside both industry and academic scientists to produce accurate and efficient code across a range of disciplines and architectures. This Centre for Doctoral Training offers an excellent opportunity to develop new algorithms, optimised for the latest hardware and accelerate their up take into industry.  


Luke MasonCDT.jpg






Contact: