Generative Models for Structured Data

You can join here

Speaker: Prof. Davide Bacciu, University of Pisa

Abstract: Structured data are an effective representation for complex information, providing a straightforward means to bridge numerical data and symbolic relationships. The lecture discusses the adaptive processing of structured data from a two-fold generative perspective. On the one hand, we consider probabilistic modelling of structured data, with scalable approaches borrowing on both Bayesian and Deep learning. On the other hand, we tackle the problem of learning to generate graph structured data.

Biography:  Davide Bacciu is Associate Professor at the Computer Science Department, University of Pisa. His research interests cover machine learning for structured data, Bayesian learning, deep learning and its intersection with generative approaches, reservoir computing, distributed and embedded learning systems, with over 160 published works on the topic. He is the coordinator of the H2020 TEACHING project as well as of Italian national and industrial projects. He has received the 2009 E.R. Caianiello Award for the best Italian Ph.D. thesis on neural networks. Davide serves as an Associate Editor of the IEEE Transactions on Neural Networks and Learning Systems. He is an IEEE Senior Member, a vice-chair of the IEEE CIS Neural Network Technical Committee, and the chair of the IEEE TF on learning for structured data. He has been serving in the board of the Italian Association for AI since 2015, from 2017 to 2021 he held the position of Secretary of the association and from 2022 he is Vice President.

Host: Prof. Cesare Alippi