cfaed Seminar Series

(Archive)

BIOTEC Green Seminar

Prof. Riccardo Zecchina , Politecnico di Torino, Italy; Dept. for Applied Science and Technology / Human Genetics Foundation, Torino

Efficient learning and generalization in networks with "material" synapses: theory and message-passing algorithms

29.05.2015 (Friday) , 11:00 - 12:30
CRTD, Auditorium left , Fetscherstraße 105 , 01307 Dresden

BIOTEC Green Seminar: Efficient learning and generalization in networks with "material" synapses: theory and message-passing algorithms

Prof. Riccardo Zecchina, Web page: http://staff.polito.it/riccardo.zecchina/

Research Activity:

The research interests of Riccardo Zecchina lie at the interface between statistical physics, computational neuroscience and computational biology. The main themes include equilibrium and out-of-equilibrium modelling, statistical physics of inverse problems for data analysis, statistical inference and combinatorial optimization, learning theory and regulatory networks. The research activity covers fundamental aspects as well as the design of efficient algorithms.

Publications:

  • Determining computational complexity from characteristic `phase transitions', Nature 400, 133 (8-July-1999), with R. Monasson, S.Kirkpatrick, B.Selman, L.Troyansky
  • Analytic and Algorithmic Solution of Random Satisfiability Problems, Science 297, 812 (2002) (Sciencexpress published on-line 27-June-2002; 10.1126/science.1073287), with M.Mezard and G.Parisi;
  • Efficient supervised learning in networks with binary synapses, C. Baldassi, A. Braunstein, N. Brunel, R. Zecchina, Proc. Nat. Acad. Sci. (PNAS) 104, 11079-11084 (2007)
  • Integrated transcriptional and competitive endogenous RNA networks are cross-regulated in permissive molecular environments, U. Ala et. al., PNAS 110, 7154 (2013)
  • 3D Protein Structure Predicted from evolutionary sequence variation, D.S. Marks et. al,  PLoS O NE 6, e28766 (2011)

Go back