Towards algorithm auditing: managing legal, ethical and technological risks of AI, ML and associated algorithms
A Koshiyama, E Kazim, P Treleaven… - Royal Society …, 2024 - royalsocietypublishing.org
Business reliance on algorithms is becoming ubiquitous, and companies are increasingly
concerned about their algorithms causing major financial or reputational damage. High …
concerned about their algorithms causing major financial or reputational damage. High …
[HTML][HTML] AI-enhanced spatial-temporal data-mining technology: New chance for next-generation urban computing
* Correspondence: wangfei@ ict. ac. cn (FW); yaodi@ ict. ac. cn (DY); liyong07@ tsinghua.
edu. cn (YL) Received: January 29, 2023; Accepted: February 19, 2023; Published Online …
edu. cn (YL) Received: January 29, 2023; Accepted: February 19, 2023; Published Online …
Investigating debiasing effects on classification and explainability
M Marchiori Manerba, R Guidotti - Proceedings of the 2022 AAAI/ACM …, 2022 - dl.acm.org
During each stage of a dataset creation and development process, harmful biases can be
accidentally introduced, leading to models that perpetuates marginalization and …
accidentally introduced, leading to models that perpetuates marginalization and …
System cards for AI-based decision-making for public policy
F Gursoy, IA Kakadiaris - arXiv preprint arXiv:2203.04754, 2022 - arxiv.org
Decisions impacting human lives are increasingly being made or assisted by automated
decision-making algorithms. Many of these algorithms process personal data for predicting …
decision-making algorithms. Many of these algorithms process personal data for predicting …
Decoding the black box: A comprehensive review of explainable artificial intelligence
O Embarak - 2023 9th International Conference on Information …, 2023 - ieeexplore.ieee.org
This review explores the current state of Explainable Artificial Intelligence (XAI). This study
looks at current advances in XAI research, as well as challenges and the future. To …
looks at current advances in XAI research, as well as challenges and the future. To …
Toward accountable and explainable artificial intelligence part one: theory and examples
Like other Artificial Intelligence (AI) systems, Machine Learning (ML) applications cannot
explain decisions, are marred with training-caused biases, and suffer from algorithmic …
explain decisions, are marred with training-caused biases, and suffer from algorithmic …
[HTML][HTML] Explaining the Behaviour of Reinforcement Learning Agents in a Multi-Agent Cooperative Environment Using Policy Graphs
M Domenech i Vila, D Gnatyshak, A Tormos… - Electronics, 2024 - mdpi.com
The adoption of algorithms based on Artificial Intelligence (AI) has been rapidly increasing
during the last few years. However, some aspects of AI techniques are under heavy scrutiny …
during the last few years. However, some aspects of AI techniques are under heavy scrutiny …
Humans supervising artificial intelligence–investigation of designs to optimize error detection
M Braun, M Greve, AB Brendel… - Journal of Decision …, 2024 - Taylor & Francis
Artificial Intelligence (AI) fundamentally changes the way we work by introducing new
capabilities. Human tasks shift towards a supervising role where the human confirms or …
capabilities. Human tasks shift towards a supervising role where the human confirms or …
Different views of interpretability
Interpretability, in the context of machine learning, means understanding the predictions
made by the machine learning algorithm, with the aim to support human decisions based on …
made by the machine learning algorithm, with the aim to support human decisions based on …
A comparative analysis of rule-based, model-agnostic methods for explainable artificial intelligence
The ultimate goal of Explainable Artificial Intelligence is to build models that possess both
high accuracy and degree of explainability. Understanding the inferences of such models …
high accuracy and degree of explainability. Understanding the inferences of such models …