Lorenza Saitta / Jean-Daniel Zucker

Lorenza Saitta is Full Professor of Computer Science at the University of Torino (Italy). She started her research activity in Pattern Recognition, moving soon to AI, specifically in the area of Fuzzy Logic for Expert Systems. In 1984 she started working in Machine Learning, thus initiating the reaserch in the field in Italy. Her first interests have been in inductive symbolic approaches. In this period, she and her research group developed the systems ML-SMART and RIGEL, which learn first-order logic concept descriptions, and have been applied to real-world industrial problems. Later, she worked on the integration of different learning strategies, involving more complex reasoning schemes, such as deduction and abduction Of this period is the implementation of the system WHY, which exploits examples and a causal model of the domain to acquire and revise first-order logic based diagnostic knowledge. More recently, she became interested in Genetic Algorithms (system REGAL) and in Cognitive Sciences. She is an Action Editor for the Machine Learning Journal, the Convener of the Research Technical Committee of the CEE founded Network Excellence for Machine Learning and Co-Director of the European Science Foundation project on Learning in Humans and Machines. She has also been responsible of, or participated to, several European Research projects. She gave an invited survey on Machine Learning at ECAI-92, and has been Invited Speaker to the Int. Joint Conf. on Artificial Intelligence (IJCAI-93), the European Conf. on Machine Learning (ECML-94), the Int. Workshop in Inductive Logic Programming (ILP-94) and the Int. Workshop on Artificial Intelligence and Cognitive Science (1994) and will give an invited talk at the 3rd Multistrategy Learning Workshop (1996). She authored (or edited) three books and more than 100 papers in journals, books and international conferences. She is (or has been) member of various journals Editorial Board and of many International Conferences Program Committees, as, for instance, the Machine Learning Conference 1992, 1993, 1994, the European Machine Learning Conference 1991, 1993, 1994, and ECAI-92. She has been Co-Chairperson of the Int. Conf. on Information Processing and Management of Uncertainty (IPMU-88) and of the Int. Symposium of Methodologies for Intelligent Systems. Jean-daniel Zucker My research focus is AI, Machine Learning, Multi-Scale Agent-based modelling of Complex Systems from Omics data integration to Environmental Decision system. I am a Former Engineer (Sup’Aéro,1985). In 1996 I got my Ph.D. in Machine Learning from Paris 6 Univ. where I became an associate professor. In 2002 I became Full Prof. at Paris 13 University. In 2008 I became a Senior Researcher at IRD. I am the director of the UMMISCO Lab. on Math. and Comput.Modeling of Complex Systems since 2014.

Abstraction is a fundamental mechanism underlying both human and artificial perception, representation of knowledge, reasoning and learning. This mechanism plays a crucial role in many disciplines, notably Computer Programming, Natural and Artificial Vision, Complex Systems, Artificial Intelligence and Machine Learning, Art, and Cognitive Sciences. This book first provides the reader with an overview of the notions of abstraction proposed in various disciplines by comparing both commonalities and differences. After discussing the characterizing properties of abstraction, a formal model, the KRA model, is presented to capture them. This model makes the notion of abstraction easily applicable by means of the introduction of a set of abstraction operators and abstraction patterns, reusable across different domains and applications. It is the impact of abstraction in Artificial Intelligence, Complex Systems and Machine Learning which creates the core of the book. A general framework, based on the KRA model, is presented, and its pragmatic power is illustrated with three case studies: Model-based diagnosis, Cartographic Generalization, and learning Hierarchical Hidden Markov Models. 抽象是人类和人工感知，知识表示，推理和学习的基础机制。这种机制在许多学科中都起着至关重要的作用，特别是计算机编程，自然和人工视觉，复杂系统，人工智能和机器学习，艺术和认知科学。本书首先通过比较通用性和差异性，为读者提供了在各个学科中提出的抽象概念的概述。在讨论了抽象的特性之后，提出了一个正式的模型KRA模型来捕获它们。通过引入一组抽象运算符和抽象模式，该模型可以轻松地应用抽象概念，这些抽象运算符和抽象模式可在不同领域和应用程序之间重用。人工智能，复杂系统和机器学习中的抽象影响是本书的核心。提出了一个基于KRA模型的通用框架，并通过三个案例研究说明了其实用性：基于模型的诊断，制图概括和学习分层隐马尔可夫模型。 （以上为google翻译）