Modeling Decisions for Artificial Intelligence: 20th International Conference, MDAI 2023, Umea, Sweden, June 19-22, 2023, Proceedings

ISBN-13: 9783031334979 / Angielski

Vicenc Torra;Yasuo Narukawa

Opis

This book constitutes the refereed proceedings of the 20th International Conference on Modeling Decisions for Artificial Intelligence, MDAI 2023, held in Umea, Sweden, during June19-22,2023. The 17 papers presented in this volume were carefully reviewed and selected from 28 submissions. Additionally, 1 invited paper were included. The papers discuss different facets of decision processes in a broad sense and present research in data science, data privacy, aggregation functions, human decision making, graphs and social networks, and recommendation and search. The papers are organized in the following topical sections: Decision making and uncertainty; Machine Learning and data science; and Data privacy.

Spis treści

Logic Aggregators and Their Implementations.- Decision making and uncertainty.- Multi-Target Decision Making under Conditions of Severe Uncertainty.- Constructive set function and extraction of a k-dimensional element.- Coherent upper conditional previsions defined by fractal outer measures to represent the unconscious activity of human brain.- Discrete chain-based Choquet-like operators.- On a new generalization of decomposition integrals.- Bipolar OWA operators with continuous input function.- Machine Learning and data science.- Cost-constrained group feature selection using information theory.- Conformal Prediction for Accuracy Guarantees in Classification with Reject Option.- Adapting the Gini's index for solving Predictive Tasks.- Bayesian logistic model for positive and unlabeled data.- A goal-oriented specification language for reinforcement learning.- Improved Spectral Norm Regularization for Neural Networks.- Preprocessing Matters: Automated Pipeline Selection for Fair Classification.- Predicting Next Whereabouts using Deep Learning.- A Generalization of Fuzzy c-Means with Variables Controlling Cluster Size.- Data privacy.- Local Differential Privacy Protocol for Making Key{Value Data Robust against Poisoning Attacks.- Differential Privacy through Noise-Graph Addition.