Explainable AI (XAI) has emerged in recent years as a set of techniques and methodologies to interpret explain machine learning (ML) predictors. To date, many initiatives have been proposed. Nevertheless, current research efforts mainly focus on methods tailored specific ML tasks algorithms, such image classification sentiment analysis. However, explanation are still embryotic, they target expe...

Peer prediction mechanisms incentivize self-interested agents to truthfully report their signals even in the absence of verification by comparing agents’ reports with peers. We propose two new mechanisms, Source and Target Differential Prediction, prove very strong guarantees for a general setting. Our Prediction are strongly truthful : Truth-telling is strict Bayesian Nash equilibrium. Also, t...

Abstract We contribute to the field of Ramsey-type equilibrium models with heterogeneous agents. To this end, we state such a model in time-continuous and time-discrete form, which latter case leads finite-dimensional mixed complementarity problem. prove existence solutions problem using theory variational inequalities present further properties its solutions. Finally, compute growth dynamics c...

In this article we describe a new methodology to facilitate communications between heterogeneous negotiation agents; in particular we present an ontology solution which allows the publication and sharing of communication primitives over Internet. Traditional negotiation systems exchange messages based on particular language definitions implicitly encoded, giving different syntax and semantics t...