University of Padova


Preferences and Ethical Principles in Decision Making

AAAI Conferences

If we want AI systems to make decisions, or to support humans in making them, we need to make sure they are aware of the ethical principles that are involved in such decisions, so they can guide towards decisions that are conform to the ethical principles. Complex decisions that we make on a daily basis are based on our own subjective preferences over the possible options. In this respect, the CP-net formalism is a convenient and expressive way to model preferences over decisions with multiple features. However, often the subjective preferences of the decision makers may need to be checked against exogenous priorities such as those provided by ethical principles, feasibility constraints, or safety regulations. Hence, it is essential to have principled ways to evaluate if preferences are compatible with such priorities. To do this, we describe also such priorities via CP-nets and we define a notion of distance between the ordering induced by two CPnets. We also provide tractable approximation algorithms for computing the distance and we define a procedure that uses the distance to check if the preferences are close enough to the ethical principles. We then provide an experimental evaluation showing that the quality of the decision with respect to the subjective preferences does not significantly degrade when conforming to the ethical principles.


Modelling Ethical Theories Compactly

AAAI Conferences

Recently a large attention has been devoted to the ethical issues arising around the design and the implementation of artificial agents. This is due to the fact that humans and machines more and more often need to collaborate to decide on actions to take or decisions to make. Such decisions should be not only correct and optimal from the point of view of the overall goal to be reached, but should also agree to some form of moral values which are aligned to the human ones. Examples of such scenarios can be seen in autonomous vehicles, medical diagnosis support systems, and many other domains, where humans and artificial intelligent systems cooperate. One of the main issues arising in this context regards ways to model and reason with moral values. In this paper we discuss the possible use of AI compact preference models as a promising approach to model, reason, and embed moral values in decision support systems.


Beyond the Turing Test

AI Magazine

The articles in this special issue of AI Magazine include those that propose specific tests, and those that look at the challenges inherent in building robust, valid, and reliable tests for advancing the state of the art in AI.


Beyond the Turing Test

AI Magazine

The articles in this special issue of AI Magazine include those that propose specific tests, and those that look at the challenges inherent in building robust, valid, and reliable tests for advancing the state of the art in AI.


Letter to the Editor: Research Priorities for Robust and Beneficial Artificial Intelligence: An Open Letter

AI Magazine

The adoption of probabilistic and decision-theoretic representations and statistical learning methods has led to a large degree of integration and cross-fertilization among AI, machine learning, statistics, control theory, neuroscience, and other fields. The progress in AI research makes it timely to focus research not only on making AI more capable, but also on maximizing the societal benefit of AI. We recommend expanded research aimed at ensuring that increasingly capable AI systems are robust and beneficial: our AI systems must do what we want them to do. In summary, we believe that research on how to make AI systems robust and beneficial is both important and timely, and that there are concrete research directions that can be pursued today.


Letter to the Editor: Research Priorities for Robust and Beneficial Artificial Intelligence: An Open Letter

AI Magazine

Artificial intelligence (AI) research has explored a variety of problems and approaches since its inception, but for the last 20 years or so has been focused on the problems surrounding the construction of intelligent agents — systems that perceive and act in some environment. In this context, "intelligence" is related to statistical and economic notions of rationality — colloquially, the ability to make good decisions, plans, or inferences. The adoption of probabilistic and decision-theoretic representations and statistical learning methods has led to a large degree of integration and cross-fertilization among AI, machine learning, statistics, control theory, neuroscience, and other fields. The establishment of shared theoretical frameworks, combined with the availability of data and processing power, has yielded remarkable successes in various component tasks such as speech recognition, image classification, autonomous vehicles, machine translation, legged locomotion, and question-answering systems. As capabilities in these areas and others cross the threshold from laboratory research to economically valuable technologies, a virtuous cycle takes hold whereby even small improvements in performance are worth large sums of money, prompting greater investments in research. There is now a broad consensus that AI research is progressing steadily, and that its impact on society is likely to increase. The potential benefits are huge, since everything that civilization has to offer is a product of human intelligence; we cannot predict what we might achieve when this intelligence is magnified by the tools AI may provide, but the eradication of disease and poverty are not unfathomable. Because of the great potential of AI, it is important to research how to reap its benefits while avoiding potential pitfalls. The progress in AI research makes it timely to focus research not only on making AI more capable, but also on maximizing the societal benefit of AI. Such considerations motivated the AAAI 2008–09 Presidential Panel on Long-Term AI Futures and other projects on AI impacts, and constitute a significant expansion of the field of AI itself, which up to now has focused largely on techniques that are neutral with respect to purpose. We recommend expanded research aimed at ensuring that increasingly capable AI systems are robust and beneficial: our AI systems must do what we want them to do. The attached research priorities document [see page X] gives many examples of such research directions that can help maximize the societal benefit of AI. This research is by necessity interdisciplinary, because it involves both society and AI. It ranges from economics, law and philosophy to computer security, formal methods and, of course, various branches of AI itself. In summary, we believe that research on how to make AI systems robust and beneficial is both important and timely, and that there are concrete research directions that can be pursued today.


Equivalence Results between Feedforward and Recurrent Neural Networks for Sequences

AAAI Conferences

In the context of sequence processing, we study the relationship between single-layer feedforward neural networks,that have simultaneous access to all items composing a sequence, and single-layer recurrent neural networks which access information one step at a time.We treat both linear and nonlinear networks, describing a constructive procedure, based on linear autoencoders for sequences, that given a feedforward neural network shows how to define a recurrent neural network that implements the same function in time. Upper bounds on the required number of hidden units for the recurrent network as a function of some features of the feedforward network are given. By separating the functional from the memory component, the proposed procedure suggests new efficient learning as well as interpretation procedures for recurrent neural networks.


Gibbard–Satterthwaite Games

AAAI Conferences

The Gibbard-Satterthwaite theorem implies the ubiquity of manipulators — voters who could change the election outcome in their favor by unilaterally modifying their vote. In this paper, we ask what happens if a given profile admits several such voters. We model strategic interactions among Gibbard–Satterthwaite manipulators as a normal-form game. We classify the 2-by-2 games that can arise in this setting for two simple voting rules, namely Plurality and Borda, and study the complexity of determining whether a given manipulative vote weakly dominates truth-telling, as well as existence of Nash equilibria.


Controlling Elections by Replacing Candidates: Theoretical and Experimental Results

AAAI Conferences

We consider elections where the chair may attempt to influence the result by replacing candidates with the intention to make a specific candidate lose (destructive control). We call this form of control "replacement control" and we study its computational complexity. We focus in particular on Plurality and Veto,for which we prove that destructive control via replacing candidates is computationally difficult, and Borda for which we prove that destructive control via replacing candidates is computationally easy. To get more insight into the practical complexity of this problem, we also perform an extensive experimental study. This study shows that the theoretical computational complexity results are often not reflecting the practical difficulty of controlling elections by replacing candidates.


Binary Aggregation by Selection of the Most Representative Voters

AAAI Conferences

In binary aggregation, each member of a group expresses yes/no choices regarding several correlated issues and we need to decide on a collective choice that accurately reflects the views of the group. A good collective choice will minimise the distance to each of the individual choices, but using such a distance-based aggregation rule is computationally intractable. Instead, we explore a class of low-complexity aggregation rules that select the most representative voter in any given situation and return that voter's choice as the outcome.