Thursday, February 16th

Carlo Vittorio Cannistraci



I will present our research at the Center for Complex Network Intelligence (CCNI) that I recently established in the Tsinghua Laboratory of Brain and Intelligence at Tsinghua University in Beijing. We adopt a transdisciplinary approach integrating information theory, machine learning, and network science to investigate the physics of adaptive complex networked systems at different scales, from molecules to ecological and social systems, with particular attention to biology and medicine and a new emerging interest for the analysis of complex big data in social and economic science. Our theoretical effort is to translate advanced mathematical paradigms typically adopted in theoretical physics (such as topology, network, and manifold theory) to characterize many-body interactions in complex systems. We apply the theoretical frameworks we invent in the mission to develop computational tools for the machine intelligent systems and network analysis. We deal with: the prediction of wiring in networks, sparse deep learning, network geometry, and multiscale-combinatorial marker design for the quantification of topological modifications in complex networks. This talk will focus on two main theoretical innovations. Firstly, the development of machine learning for topological estimation of nonlinear relations in high-dimensional data (or in complex networks) and its relevance for applications in big data, with a particular emphasis on brain connectome analysis. Secondly, we will discuss the Local Community Paradigm (LCP), and its recent extension to the Cannistraci-Hebb network automata, which are brain-inspired theories proposed to model local-topology-dependent link-growth in complex networks and therefore are useful to devise topological methods for link prediction in sparse deep learning, or monopartite and bipartite networks, such as molecular drug-target interactions and product-consumer networks.