Search Results for author:
Found 22 papers, 3 papers with code
Counterfactual Influence in Markov Decision Processes
Our work addresses a fundamental problem in the context of counterfactual inference for Markov Decision Processes (MDPs).
Explaining Image Classifiers
We focus on explaining image classifiers, taking the work of Mothilal et al. [2021] (MMTS) as our point of departure.
MRxaI: Black-Box Explainability for Image Classifiers in a Medical Setting
Existing tools for explaining the output of image classifiers can be divided into white-box, which rely on access to the model internals, and black-box, agnostic to the model.
You Only Explain Once
In this paper, we propose a new black-box explainability algorithm and tool, YO-ReX, for efficient explanation of the outputs of object detectors.
Clustered Policy Decision Ranking
Policies trained via reinforcement learning (RL) are often very complex even for simple tasks.
Multiple Different Black Box Explanations for Image Classifiers
Existing explanation tools for image classifiers usually give only a single explanation for an image's classification.
Causal Analysis of the TOPCAT Trial: Spironolactone for Preserved Cardiac Function Heart Failure
We describe the results of applying causal discovery methods on the data from a multi-site clinical trial, on the Treatment of Preserved Cardiac Function Heart Failure with an Aldosterone Antagonist (TOPCAT).
Equality of Effort via Algorithmic Recourse
This paper proposes a method for measuring fairness through equality of effort by applying algorithmic recourse through minimal interventions.
A Causal Analysis of Harm
In this paper we formally define a qualitative notion of harm that uses causal models and is based on a well-known definition of actual causality (Halpern, 2016).
Quantifying Harm
In a companion paper (Beckers et al. 2022), we defined a qualitative notion of harm: either harm is caused, or it is not.
Domain Knowledge in A*-Based Causal Discovery
Causal discovery has become a vital tool for scientists and practitioners wanting to discover causal relationships from observational data.
A Study of Demographic Bias in CNN-based Brain MR Segmentation
We find significant sex and race bias effects in segmentation model performance.
Vision Checklist: Towards Testable Error Analysis of Image Models to Help System Designers Interrogate Model Capabilities
Robustness evaluations like our checklist will be crucial in future safety evaluations of visual perception modules, and be useful for a wide range of stakeholders including designers, deployers, and regulators involved in the certification of these systems.
Causal policy ranking
Policies trained via reinforcement learning (RL) are often very complex even for simple tasks.
Transfer learning with causal counterfactual reasoning in Decision Transformers
In this study, we apply causal reasoning in the offline reinforcement learning setting to transfer a learned policy to new environments.
Explanations for Occluded Images
Existing algorithms for explaining the output of image classifiers perform poorly on inputs where the object of interest is partially occluded.
Safety Synthesis Sans Specification
We define the problem of learning a transducer ${S}$ from a target language $U$ containing possibly conflicting transducers, using membership queries and conjecture queries.
Ranking Policy Decisions
Policies trained via Reinforcement Learning (RL) are often needlessly complex, making them difficult to analyse and interpret.
Combining Experts' Causal Judgments
We formally define the notion of an effective intervention, and then consider how experts' causal judgments can be combined in order to determine the most effective intervention.
Explaining Image Classifiers using Statistical Fault Localization
The black-box nature of deep neural networks (DNNs) makes it impossible to understand why a particular output is produced, creating demand for "Explainable AI".
Causality and Responsibility for Formal Verification and Beyond
The theory of actual causality, defined by Halpern and Pearl, and its quantitative measure - the degree of responsibility - was shown to be extremely useful in various areas of computer science due to a good match between the results it produces and our intuition.
The Computational Complexity of Structure-Based Causality
Halpern and Pearl introduced a definition of actual causality; Eiter and Lukasiewicz showed that computing whether X=x is a cause of Y=y is NP-complete in binary models (where all variables can take on only two values) and\ Sigma_2^P-complete in general models.
