Learning from Constraints

• La présentation sera en anglais (peut-être plus accessible que l'italien)

• Rémi Coulom, jusqu'à très récemment auteur du meilleur programme du jeu de go au monde, parlera pendant une vingtaine de minutes sur CrazyStone, AlphaGo, et l'avenir de l'IA.

Marco Gori, en visite de l'University of Siena, parlera sur "Learning from Constraints".

Résumé :

In this talk, I propose a functional framework to understand the emergence of intelligence in agents exposed to examples and knowledge granules. The theory is based on the abstract notion of constraint, which provides a representation of knowledge granules gained from the interaction with the environment. I give some representation theorems that extend the classic framework of kernel machines in such a way to incorporate logic formalisms, like first-order logic. This is made possible by the unification of continuous and discrete computational mechanisms in the same functional framework, so as any stimulus, like supervised examples and logic predicates, is translated into a constraint. The prescribed structure, which comes out from constrained variational calculus, is guided by a sort of parsimonious match of the constraints, and it is shown that only support constraints are involved, which nicely generalize the notion of support vectors in SVM. Finally, I present some experimental results that also include the verification of new constraints.

Bio

Marco Gori, University of Siena

Marco Gori received the Ph.D. degree in 1990 from Università di Bologna, Italy, working partly at the School of Computer Science (McGill University, Montreal). In 1992, he became an Associate Professor of Computer Science at Università di Firenze and, in November 1995, he joint the Università di Siena, where he is currently full professor of computer science.

His main interests are in machine learning with applications to pattern recognition, Web mining, and game playing. He is especially interested in bridging logic and learning Marco Gori received the Ph.D. degree in 1990 from Università di Bologna, Italy, and in the connections between symbolic and sub-symbolic representation of working partly at the School of Computer Science (McGill University, Montreal). In information. He was the leader of the WebCrow project for automatic solving of 1992, he became an Associate Professor of Computer Science at Università di Firenze crosswords, that outperformed human competitors in an official competition which and, in November 1995, he joint the Universitá di Siena, where he is currently full took place during the ECAI-06 conference. As a follow up of this grand challenge he founded QuestIt, a spin-off company of the University of Siena, working in the field of question-answering. He is co-author of the book "Web Dragons: Inside the myths of His main interests are in machine learning with applications to pattern recognition, search engines technologies," Morgan Kauffman (Elsevier), 2006.

Web mining, and game playing. He is especially interested in bridging logic and learning and in the connections between symbolic and sub-symbolic representation of Dr. Gori serves (has served) as an Associate Editor of a number of technical journals information. He is the leader of the WebCrow project for automatic solving of crosswords, that outperformed human competitors in an official competition which related to his areas of expertise, he has been the recipient of best paper awards, and took place within the ECAI-06 conference. As a follow up of this grand challenge, he keynote speakers in a number of international conferences. He was the Chairman of the founded QuestIt, a spin-off company of the University of Siena, working in the field Italian Chapter of the IEEE Computational Intelligence Society, and the President of the of question-answering. He is co-author of the book “Web Dragons: Inside the myths Italian Association for Artificial Intelligence. of search engines technologies,” Morgan Kauffman (Elsevier), 2006. He is a fellow of the IEEE, ECCAI, IAPR. He is in the list of top Italian scientists kept by the VIA-Academy (http://www.topitalianscientists.org/top_italian_scientists.aspx)

Lecture

https://www.meetup.com/Nantes-Machine-Learning-Meetup/files/