LYRICS: A Unified Framework for Learning and Inference with Constraints

In spite of the amazing results obtained by deep learning in many applications, a real intelligent behavior of an agent acting in a complex environment is likely to require some kind of higher-level symbolic inference. Therefore, there is a clear need for the definition of a general and tight integration between low-level tasks, processing sensorial data that can be effectively elaborated using deep learning techniques, and the abstract reasoning that allows humans to take decisions in complex environments. In this seminar, we illustrate LYRICS, a general framework for learning and inference with constraints. Special attention will be given to the case in which constraints are represented by Fuzzy First Order Logic formulas.


PhD student Giuseppe Marra from the University of Firenze and University of Siena will join the team IDA from January to March 2019. He studies Smart Computing and his research activities are focused on machine learning and its applications for the development of conversational agents. Apart from computer science, Giuseppe is also passionate about post-impressionist classical music. If you want to meet him in person, come to the lecture!

January 17, 2019 (Thursday)
Room 205, Building G, Karlovo nám. 13