Over the recent year, Neural Architecture Search (NAS) has attracted a lot of attention. While being able to automate the discovery of better performing neural architectures than hand-crafted ones, it comes at a great price, requiring thousands of GPU hours to perform the search. The Zero Cost NAS competition challenges the participants to design efficient proxies for NAS, using negligible computational resources to evaluate neural architectures.
In collaboration with the AutoCAML team at Samsung AI Cambridge (led by Dr. Hongkai Wen), our research students, Lichuan Xiang and Youyang Sha, proposed new zero-cost NAS metrics that exploit the compressibility of neural networks. Our metrics are extremely efficient to run (reducing search cost from weeks/days to minutes), and achieves impressive results across multiple search spaces and datasets. In the competition, our teams won both the 1st and 2nd places (using different scoring functions), and the performance gap with the 3rd winning team is almost 2x. Checkout our poster here.
We are delighted to report that Dr Long Tran-Thanh has received a AIJ Prominent Paper Award for his first-authored paper, Efficient crowdsourcing of unknown experts using bounded multi-armed bandits, published in 2014 at Artificial Intelligence (AIJ), a premier journal in the field of artificial intelligence. The AIJ Prominent Paper Award recognises outstanding papers published in the journal in the last seven years that are exceptional in their significance and impact.
The paper developed the first comprehensive framework for the rigorous and principled mathematical analysis of task allocation algorithms in crowdsourcing systems. In addition, the paper proposed bounded bandits, a new sequential decision making model to solve task allocation problems with resource constraints. The work has had a significant impact on subsequent work carried out in both industry and academia. The award will be presented at IJCAI 2021, a top tier international conference in artificial intelligence.
We are pleased to report that Dr Simon Graham, Senior Research Fellow from the Department of Computer Science, has received a SEM Faculty Thesis Prize.
Each year, the Faculty of Science, Engineering and Medicine (SEM) funds a prize for the best PhD/EngD thesis in each of its ten departments. Each department nominates a winner out of the applications received after a judging process as determined by the Faculty.
Dr Simon Graham commented regarding his award:
My research focussed on the development of computational tools for the automatic analysis of digitised cancerous tissue samples. Now, I am continuing my research in the area of computational pathology and soon hope to see it utilised in a clinical setting, where it may help improve cancer recognition and treatment planning. I would like to thank my supervisor Professor Nasir Rajpoot and all my collaborators within the Tissue Image Analytics Centre and at University Hospitals Coventry and Warwickshire for their support during my PhD.
The program focusses on using AI to address some of the world’s biggest societal challenges. Dr. Tran-Thanh’s project, titled Incentive Engineering and Truthful Mechanisms for Grassland Quality and Local Market Price Estimation in Africa, will address the problem of holistic grazing and pasture management in East Africa. The main objectives of the project are: (i) to identify the most efficient ways to evaluate the overall quality of different grazing areas; (ii) to develop a user friendly recommendation system that chooses the next best grazing areas for pastoralists, that takes into account the holistic aspect of pasture management; and (iii) to incentivise pastoralists to truthfully report their activities in order to further improve the system’s predictive ability. The project is a collaboration between the University of Warwick and AfriScout.
We are delighted to report that Dr Greg Watson and Dr Lin Gui have been promoted to, respectively, Senior Teaching Fellow and Senior Research Fellow, effective from 1 August 2021. Quoting from their recommendations,
What particularly stands out ... is the virtuous circle of (1) Dr Watson’s continual striving for advancing his teaching expertise, evidenced by the extensive courses he has both attended and contributed to, (2) the strong two-way links between Dr Watson’s development and his teaching practice (and that of his peers), evidenced by the various different changes and improvements that he introduced in the classroom based on his scholarly educational investigations, and (3) the consistent very positive feedback from different groups of students as well as colleagues.
Dr Lin Gui is one of the most successful postdoctoral researchers in the recent history of the Department, and is continuing his research career with us after a prestigious two-year Marie Curie fellowship. He has been building a solid and high-flying international reputation, underpinned by an impressive trajectory of high-quality publications. Dr Gui’s initiative and emerging independence are in particular reflected in his contributions to substantial successful funding proposals.
it remains to say many congratulations!
EPSRC funding awarded to Prof. Yulan He and Prof. Rob Procter on developing an AI solution for tackling “infodemic”
Prof. Yulan He and Prof. Rob Procter have been awarded funding from the EPSRC under the UKRI’s COVID-19 call. During the COVID-19 pandemic, national and international organisations are using social media and online platforms to communicate information about the virus to the public. However, propagation of misinformation has also become prevalent. This can strongly influence human behaviour and negatively impact public health interventions, so it is vital to detect misinformation in a timely manner. This project aims to develop machine learning algorithms for automatic collection of external evidence relating to COVID-19 and assessment of veracity of claims.