Related papers: Algorithmic Transparency and Manipulation
Efforts to promote equitable public policy with algorithms appear to be fundamentally constrained by the "impossibility of fairness" (an incompatibility between mathematical definitions of fairness). This technical limitation raises a…
Mechanistic interpretability aims to understand the computational mechanisms underlying neural networks' capabilities in order to accomplish concrete scientific and engineering goals. Progress in this field thus promises to provide greater…
Algorithmic processes are increasingly employed to perform managerial decision making, especially after the tremendous success in Artificial Intelligence (AI). This paradigm shift is occurring because these sophisticated AI techniques are…
In this work, we study some novel applications of conformal inference techniques to the problem of providing machine learning procedures with more transparent, accurate, and practical performance guarantees. We provide a natural extension…
The rapid development of generative artificial intelligence (AI) technologies raises concerns about the accountability of sociotechnical systems. Current generative AI systems rely on complex mechanisms that make it difficult for even…
Artificial Intelligence based systems increasingly use personalization to provide users with relevant content, products, and solutions. Personalization is intended to support users and address their respective needs and preferences.…
People are often reluctant to incorporate information produced by algorithms into their decisions, a phenomenon called ``algorithm aversion''. This paper shows how algorithm aversion arises when the choice to follow an algorithm conveys…
In recent years, there has been an increasing awareness of both the public and scientific community that algorithmic systems can reproduce, amplify, or even introduce unfairness in our societies. These lecture notes provide an introduction…
In the current era, people and society have grown increasingly reliant on artificial intelligence (AI) technologies. AI has the potential to drive us towards a future in which all of humanity flourishes. It also comes with substantial risks…
Algorithmic bias has been the subject of much recent controversy. To clarify what is at stake and to make progress resolving the controversy, a better understanding of the concepts involved would be helpful. The discussion here focuses on…
Most organizations adjust their statistical forecasts (e.g. on sales) manually. Forecasting Support Systems (FSS) enable the related process of automated forecast generation and manual adjustments. As the FSS user interface connects user…
With machine learning models being increasingly used to aid decision making even in high-stakes domains, there has been a growing interest in developing interpretable models. Although many supposedly interpretable models have been proposed,…
Over the last decade, adversarial attack algorithms have revealed instabilities in deep learning tools. These algorithms raise issues regarding safety, reliability and interpretability in artificial intelligence; especially in high risk…
This paper addresses the critical challenge of building consumer trust in AI-powered customer engagement by emphasising the necessity for transparency and accountability. Despite the potential of AI to revolutionise business operations and…
Algorithmic and data bias are gaining attention as a pressing issue in popular press - and rightly so. However, beyond these calls to action, standard processes and tools for practitioners do not readily exist to assess and address unfair…
The paper investigates whether and how AI systems can realize states of uncertainty. By adopting a functionalist and behavioral perspective, it examines how symbolic, connectionist and hybrid architectures make room for uncertainty. The…
Clearly, socio-economic freedom requires some extent of transparency regarding the implications of choices. In this paper, we review some established mechanisms for achieving such transparency, without any claim to completeness, and briefly…
Amidst the wide popularity of imitation learning algorithms in robotics, their properties regarding hyperparameter sensitivity, ease of training, data efficiency, and performance have not been well-studied in high-precision…
Algorithmic decision-making systems are increasingly used throughout the public and private sectors to make important decisions or assist humans in making these decisions with real social consequences. While there has been substantial…
Deep learning still has drawbacks in terms of trustworthiness, which describes a comprehensible, fair, safe, and reliable method. To mitigate the potential risk of AI, clear obligations associated to trustworthiness have been proposed via…