May 9, 2o23. 3PM (Rescheduled from November 2022) Room: TG23 (Town Hall Building) Speaker: Gunel Jahangirova Title: Mutation Testing of Deep Learning Systems Abstract: Deep Learning (DL) is increasingly adopted to solve complex tasks such as image recognition or autonomous driving. Companies are considering the inclusion of DL components in production systems, but one of […]
Colloquium
March 9th, 2023. Thursday. 3PM. Room: TG23 (Town Hall Building) Speaker: Murdoch J. Gabbay (Heriot-Watt University) Title: A broadly Marxian analysis of blockchain and cryptocurrencies Abstract: Bitcoin sought to transfer the means of production of money from the state to individuals; Karl Marx would probably have been delighted. It hasn’t worked out quite how the […]
February 8th, 2023. Wednesday. 3PM. Postponed due to illness. New date to be announced. TG23 (Town Hall Building) Speaker: Samson Abramsky (University College, London) Title: Contextuality: from quantum mechanics to logic, language and information Abstract: Contextuality is the key non-classical feature of quantum mechanics, which has been used to show various forms of quantum advantage […]
January 11, 2023. Wednesday. 3.30PM. TG23 (Town Hall Building) Speaker: Edith Elkind Title: Learning axes from samples: single-peaked preferences and beyond Abstract: We consider a society where voters, who participate in an election, report their preferences over candidates, and these preferences are one-dimensional, i.e., consistent with the candidates being ordered on a left-to-right axis. We […]
November 16, 2022. Wednesday. 3PM Room: TG23 (Town Hall Building) Speaker: Ranko Lazic Title: Adversarial Reprogramming Revisited Abstract: TL;DR: We show that neural networks with random weights are susceptible to adversarial reprogramming, and that in some settings training the network can cause its adversarial reprogramming to fail. Adversarial reprogramming, introduced by Elsayed, Goodfellow, and Sohl-Dickstein, […]
November 10, 2022. Thursday. 3PM Room: TG23 (Town Hall Building) Speaker: Ghislain Landry Tsafack Title: Making Models Work: How an Optimised ML Lifecycle Can Drive Better ROI Abstract: The potential of Artificial Intelligence (AI) continues to take centre stage in discussions around innovation. Realizing such potential is unfortunately not as straightforward as it may seem. […]
October 12, 2022. Wednesday. 3PM Room: TG23 (Town Hall Building) Speaker: Ilina Stoilkovska Title: Automated Logic-Based Reasoning for Analyzing Prime Video Code Abstract: Developers working in Prime Video are constantly innovating, introducing new features, and improving the performance of the Prime Video application. Each modification of the Prime Video application code is required to pass […]
20 June 2022, Monday. 3PM. London Time. Online over Zoom. Title Bio-inspired Neural Architecture Search Speaker Wei Pang, Heriot-Watt University Abstract In this talk I will present the work of our lab over the last three years on bio-inspired Neural Architecture Search (NAS). I will first present DeepSwarm, an NAS system that makes use of […]
16 May 2022, Monday. 3PM. London Time. Online over Zoom. Title: Fair Division: A theoretical and a practical perspective Speaker: Maria Kyropoulou, University of Essex Abstract: In this talk I will present two different perspectives in fair division research. A common underlying concept is that of envy-freeness, a natural and widely adopted notion of fairness. […]
25 April 2022, Monday. 3PM. London Time. Online over Zoom Title: Targeted Ads, Data Openness, Digital Power: Reasons to be Cheerful” Speaker: Sam Gilbert, University of Cambridge Abstract Since the Cambridge Analytica scandal, public discussion of data and digital technology has focused on the threats big tech companies’ business models pose to individuals’ rights and freedoms. However, […]