Marcello Pelillo Knihy

Experts from disciplines that range from computer science to philosophy consider the challenges of building AI systems that humans can trust. Artificial intelligence-based algorithms now marshal an astonishing range of our daily activities, from driving a car ("turn left in 400 yards") to making a purchase ("products recommended for you"). How can we design AI technologies that humans can trust, especially in such areas of application as law enforcement and the recruitment and hiring process? In this volume, experts from a range of disciplines discuss the ethical and social implications of the proliferation of AI systems, considering bias, transparency, and other issues. The contributors, offering perspectives from computer science, engineering, law, and philosophy, first lay out the terms of the discussion, considering the "ethical debts" of AI systems, the evolution of the AI field, and the problems of trust and trustworthiness in the context of AI. They go on to discuss specific ethical issues and present case studies of such applications as medicine and robotics, inviting us to shift the focus from the perspective of a "human-centered AI" to that of an "AI-decentered humanity." Finally, they consider the future of AI, arguing that, as we move toward a hybrid society of cohabiting humans and machines, AI technologies can become humanity's allies.

This accessible text/reference presents a coherent overview of the emerging field of non-Euclidean similarity learning. The book presents a broad range of perspectives on similarity-based pattern analysis and recognition methods, from purely theoretical challenges to practical, real-world applications. The coverage includes both supervised and unsupervised learning paradigms, as well as generative and discriminative models. Topics and features: explores the origination and causes of non-Euclidean (dis)similarity measures, and how they influence the performance of traditional classification algorithms; reviews similarity measures for non-vectorial data, considering both a “kernel tailoring” approach and a strategy for learning similarities directly from training data; describes various methods for “structure-preserving” embeddings of structured data; formulates classical pattern recognition problems from a purely game-theoretic perspective; examines two large-scale biomedical imaging applications.

This book constitutes the proceedings of the First International Workshop on Similarity Based Pattern Recognition, SIMBAD 2011, held in Venice, Italy, in September 2011. The 16 full papers and 7 poster papers presented were carefully reviewed and selected from 35 submissions. The contributions are organized in topical sections on dissimilarity characterization and analysis; generative models of similarity data; graph-based and relational models; clustering and dissimilarity data; applications; spectral methods and embedding.

This book constitutes the refereed proceedings of the International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition, EMMCVPR'97, held in Venice, Italy, in May 1997. The book presents 29 revised full papers selected from a total of 62 submissions. Also included are four full invited papers and a keynote paper by leading researchers. The volume is organized in sections on contours and deformable models, Markov random fields, deterministic methods, object recognition, evolutionary search, structural models, and applications. The volume is the first comprehensive documentation of the application of energy minimization techniques in the areas of compiler vision and pattern recognition.