School of Computer Science
  
 

Coronavirus (COVID-19)

See latest advice for UoN community and details of how to report symptoms or test results

Image of Luke Rose

Luke Rose

EngD Student | Reconstruction and Optimisation of Construction Materials using Generative Adversarial Networks,

Contact

Biography

Originally from Kent, I moved to Nottingham in 2015 to study Computer Science with Artificial Intelligence in the School of Computer Science at the University of Nottingham. Upon completing my bachelors, I was offered a place in the EPSRC Centre for Doctoral Training for Carbon Capture & Storage and Cleaner Fossil Energy (CCS & CFE CDT). I am currently working to obtain my Doctor of Engineering, working in the Nottingham Transportation Engineering Centre (NTEC) and the Computer Optimisation Lab (COL), utilising Generative Adversarial Networks of various forms, to optimise the production process of asphalt pavements.

Teaching Summary

Operating Systems & Concurrency Module Support Assistant

Algorithms Correctness and Efficiency Module Support Assistant and Tutorial Tutor

Computer Science 3rd Year Dissertation Assistant Co-Supervisor

Research Summary

Generative Adversarial Networks (GANs) are a relatively new format of Machine Learning model which play a "zero-sum" game involving two Artificial Neural Networks; one being a "generator" that… read more

Current Research

Generative Adversarial Networks (GANs) are a relatively new format of Machine Learning model which play a "zero-sum" game involving two Artificial Neural Networks; one being a "generator" that creates novel "forged" solutions based on previously seen samples and a "discriminator" that determines if the output of the generator is real or synthetic.

Such a powerful model can be used to create solutions to problems that through other methods would be far too computationally expensive. In my research I am using GANs to manufacture optimal materials based on porous material CT Scan data (the actual data) and virtual aggregate packing simulations (the forged data).

Past Research

Stock Market Prediction & Trading Automation using Machine Learning

School of Computer Science

University of Nottingham
Jubilee Campus
Wollaton Road
Nottingham, NG8 1BB

For all enquires please visit:
www.nottingham.ac.uk/enquire