Photo of Dr Lorenzo Livi

Dr Lorenzo Livi

Lecturer in Data Analytics


Telephone: 01392 724556

Extension: (Streatham) 4556

Home page for additional information:

Dr. Lorenzo Livi is a Lecturer (Assistant Professor) in Data Analytics with the Department of Computer Science at the University of Exeter, UK. He received the B.Sc. and M.Sc. degrees from the Department of Computer Science, Sapienza University of Rome, Italy, in 2007 and 2010, respectively, and the Ph.D. degree from the Department of Information Engineering, Electronics, and Telecommunications at Sapienza University of Rome, in 2014. From January 2014 until April 2016, he was a Post Doctoral Fellow at Ryerson University, Toronto, Canada. From May 2016 until September 2016, he was a Post Doctoral Fellow at the Politecnico di Milano, Italy and Universita' della Svizzera Italiana, Lugano, Switzerland.

His main research interests lie at the intersection of computational intelligence and complex dynamical systems, with particular emphasis on graph-based methods. He works on both theoretical and methodological aspects of machine learning and pattern recognition problems (such as classification and clustering), focusing on the analysis of non-geometric input spaces (i.e., input spaces with no trivial geometric structure).  He is also studying problems involving the analysis of (real-world) complex dynamical systems by means of advanced methods of time series analysis. Such methods are conceived to provide a characterization of the underlying (dynamic) system in terms of numerical features. Examples include multifractal analysis of time series, recurrence analysis, and spectral analysis of complex (dynamical) networks. More recently, he started investigating recurrent neural networks (e.g., echo state networks) with the purpose of analysing their dynamical properties and related computational capability. In this direction, he is focusing on unsupervised learning and methods that link notions borrowed from research on complex systems (e.g., criticality) with neural networks.
He is interested in applications involving the analysis of biochemical networks and biophysical systems. His main field of expertise is protein molecules, where he worked on both classical structure-function problems (e.g., prediction of solubility degree) and on characterization of particular dynamical features (e.g., diffusion of energy and information in protein structures). Finally, he is also working on structural and dynamical aspects related to folding problems, e.g., finding universal features that characterize protein three-dimensional conformations (i.e., native structures).