33 citations · 46 across the 7 of their papers we have counts for
4 papers · 1 filter
Information based explanation methods for deep learning agents -- with applications on large open-source chess models
Patrik Hammersborg, Inga Strümke
With large chess-playing neural network models like AlphaZero contesting the state of the art within the world of computerised chess, two challenges present themselves: The questio…
Reinforcement Learning in an Adaptable Chess Environment for Detecting Human-understandable Concepts
Patrik Hammersborg, Inga Strümke
Self-trained autonomous agents developed using machine learning are showing great promise in a variety of control settings, perhaps most remarkably in applications involving autono…
Socioeconomic disparities and COVID-19: the causal connections
Tannista Banerjee, Ayan Paul, Vishak Srikanth +1
The analysis of causation is a challenging task that can be approached in various ways. With the increasing use of machine learning based models in computational socioeconomics, ex…
Shapley values for feature selection: The good, the bad, and the axioms
Daniel Fryer, Inga Strümke, Hien Nguyen
The Shapley value has become popular in the Explainable AI (XAI) literature, thanks, to a large extent, to a solid theoretical foundation, including four "favourable and fair" axio…