290 citations · 469 across the 35 of their papers we have counts for
36 papers
Counterfactual Explanations via Locally-guided Sequential Algorithmic Recourse
Edward A. Small, Jeffrey N. Clark, Christopher J. McWilliams +4
Counterfactuals operationalised through algorithmic recourse have become a powerful tool to make artificial intelligence systems explainable. Conceptually, given an individual clas…
Capturing Requirements for a Data Annotation Tool for Intensive Care: Experimental User-Centered Design Study
Marceli Wac, Raul Santos-Rodriguez, Chris McWilliams +1
Intensive care units (ICUs) are complex and data-rich environments. Data routinely collected in the ICUs provides tremendous opportunities for machine learning, but their use comes…
TraCE: Trajectory Counterfactual Explanation Scores
Jeffrey N. Clark, Edward A. Small, Nawid Keshtmand +5
Counterfactual explanations, and their associated algorithmic recourse, are typically leveraged to understand, explain, and potentially alter a prediction coming from a black-box c…
Privacy in Multimodal Federated Human Activity Recognition
Alex Iacob, Pedro P. B. Gusmão, Nicholas D. Lane +5
Human Activity Recognition (HAR) training data is often privacy-sensitive or held by non-cooperative entities. Federated Learning (FL) addresses such concerns by training ML models…
What You Hear Is What You See: Audio Quality Metrics From Image Quality Metrics
Tashi Namgyal, Alexander Hepburn, Raul Santos-Rodriguez +2
In this study, we investigate the feasibility of utilizing state-of-the-art image perceptual metrics for evaluating audio signals by representing them as spectrograms. The encourag…
FAT Forensics: A Python Toolbox for Implementing and Deploying Fairness, Accountability and Transparency Algorithms in Predictive Systems
Kacper Sokol, Alexander Hepburn, Rafael Poyiadzi +3
Predictive systems, in particular machine learning algorithms, can take important, and sometimes legally binding, decisions about our everyday life. In most cases, however, these s…
Self-Supervised Multimodal Fusion Transformer for Passive Activity Recognition
Armand K. Koupai, Mohammud J. Bocus, Raul Santos-Rodriguez +2
The pervasiveness of Wi-Fi signals provides significant opportunities for human sensing and activity recognition in fields such as healthcare. The sensors most commonly used for pa…
Sampling Based On Natural Image Statistics Improves Local Surrogate Explainers
Ricardo Kleinlein, Alexander Hepburn, Raúl Santos-Rodríguez +1
Many problems in computer vision have recently been tackled using models whose predictions cannot be easily interpreted, most commonly deep neural networks. Surrogate explainers ar…
Multi-lingual agents through multi-headed neural networks
J. D. Thomas, R. Santos-Rodríguez, R. Piechocki +1
This paper considers cooperative Multi-Agent Reinforcement Learning, focusing on emergent communication in settings where multiple pairs of independent learners interact at varying…
Understanding surrogate explanations: the interplay between complexity, fidelity and coverage
Rafael Poyiadzi, Xavier Renard, Thibault Laugel +2
This paper analyses the fundamental ingredients behind surrogate explanations to provide a better understanding of their inner workings. We start our exposition by considering glob…
On the overlooked issue of defining explanation objectives for local-surrogate explainers
Rafael Poyiadzi, Xavier Renard, Thibault Laugel +2
Local surrogate approaches for explaining machine learning model predictions have appealing properties, such as being model-agnostic and flexible in their modelling. Several method…
On the relation between statistical learning and perceptual distances
Alexander Hepburn, Valero Laparra, Raul Santos-Rodriguez +2
It has been demonstrated many times that the behavior of the human visual system is connected to the statistics of natural images. Since machine learning relies on the statistics o…
Self-Supervised WiFi-Based Activity Recognition
Hok-Shing Lau, Ryan McConville, Mohammud J. Bocus +2
Traditional approaches to activity recognition involve the use of wearable sensors or cameras in order to recognise human activities. In this work, we extract fine-grained physical…
Self-play Learning Strategies for Resource Assignment in Open-RAN Networks
Xiaoyang Wang, Jonathan D Thomas, Robert J Piechocki +3
Open Radio Access Network (ORAN) is being developed with an aim to democratise access and lower the cost of future mobile data networks, supporting network services with various Qo…
Hypothesis Testing for Class-Conditional Label Noise
Rafael Poyiadzi, Weisong Yang, Niall Twomey +1
In this paper we provide machine learning practitioners with tools to answer the question: is there class-conditional noise in my labels? In particular, we present hypothesis tests…
Explainers in the Wild: Making Surrogate Explainers Robust to Distortions through Perception
Alexander Hepburn, Raul Santos-Rodriguez
Explaining the decisions of models is becoming pervasive in the image processing domain, whether it is by using post-hoc methods or by creating inherently interpretable models. Whi…
Information Theory in Density Destructors
J. Emmanuel Johnson, Valero Laparra, Gustau Camps-Valls +2
Density destructors are differentiable and invertible transforms that map multivariate PDFs of arbitrary structure (low entropy) into non-structured PDFs (maximum entropy). Multiva…
Information Theory Measures via Multidimensional Gaussianization
Valero Laparra, J. Emmanuel Johnson, Gustau Camps-Valls +2
Information theory is an outstanding framework to measure uncertainty, dependence and relevance in data and systems. It has several desirable properties for real world applications…
Detecting Signatures of Early-stage Dementia with Behavioural Models Derived from Sensor Data
Rafael Poyiadzi, Weisong Yang, Yoav Ben-Shlomo +5
There is a pressing need to automatically understand the state and progression of chronic neurological diseases such as dementia. The emergence of state-of-the-art sensing platform…
bLIMEy: Surrogate Prediction Explanations Beyond LIME
Kacper Sokol, Alexander Hepburn, Raul Santos-Rodriguez +1
Surrogate explainers of black-box machine learning predictions are of paramount importance in the field of eXplainable Artificial Intelligence since they can be applied to any type…
PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance
Alexander Hepburn, Valero Laparra, Jesús Malo +2
Traditionally, the vision community has devised algorithms to estimate the distance between an original image and images that have been subject to perturbations. Inspiration was us…
FACE: Feasible and Actionable Counterfactual Explanations
Rafael Poyiadzi, Kacper Sokol, Raul Santos-Rodriguez +2
Work in Counterfactual Explanations tends to focus on the principle of "the closest possible world" that identifies small changes leading to the desired outcome. In this paper we a…
FAT Forensics: A Python Toolbox for Algorithmic Fairness, Accountability and Transparency
Kacper Sokol, Raul Santos-Rodriguez, Peter Flach
Today, artificial intelligence systems driven by machine learning algorithms can be in a position to take important, and sometimes legally binding, decisions about our everyday liv…
Online Feature Selection for Activity Recognition using Reinforcement Learning with Multiple Feedback
Taku Yamagata, Raúl Santos-Rodríguez, Ryan McConville +1
Recent advances in both machine learning and Internet-of-Things have attracted attention to automatic Activity Recognition, where users wear a device with sensors and their outputs…