Claudio Ceruti

About me

My name is Claudio Ceruti.

I'm a machine learning researcher, my main interests are deep learning and its applications, and the social impact of AI. I was a postdoc researcher at the Computer Science department of Università degli Studi di Milano. I've obtained my Ph.D. in Mathematics and Statistic for Computational Science, and my M.Sc. in Computer Science from Università degli Studi di Milano. I worked in the PHuSe laboratory and I worked with the Vision Learning Group of Dartmouth College during my Ph.D. My academic researches were mainly in deep learning, particularly the application of manifold learning techniques to gain insights on the internal behaviour of deep models. I have always been fascinated by the possibility for artificial machines to address the raw data complexity and automatically inferring knowledge from it. At the same time, the growing spread of automated reasoning, moved me to enquiry the actual impact of these technologies on society and individuals.

Publications

G. Lombardi, A. Rozza, C. Ceruti, E. Casiraghi and P. Campadelli
Minimum neighbor distance estimators of intrinsic dimension
European Conference on Machine Learning(ECML 2011)
Machine Learning and Knowledge Discovery in Databases, 374-389

A. Rozza, G. Lombardi, C. Ceruti, E. Casiraghi and P. Campadelli
Novel high intrinsic dimensionality estimators
Machine learning, 1-29, May 2012

S. Bassis, A. Rozza, C. Ceruti, G. Lombardi, E. Casiraghi and P. Campadelli
A novel intrinsic dimensionality estimator based on rank-order statistics
Proceedings of CHDD. LNCS, 2012

P. Campadelli, E. Casiraghi, C. Ceruti, G. Lombardi and A. Rozza
Local Intrinsic Dimensionality Based Features for Clustering
Image Analysis and Processing–ICIAP 2013
C. Ceruti, S. Bassis, A. Rozza, G. Lombardi, E. Casiraghi and P. Campadelli
Danco: An intrinsic dimensionality estimator exploiting angle and norm concentration
Pattern Recognition, 2014

P. Campadelli, E. Casiraghi, C. Ceruti and A. Rozza
Intrinsic dimension estimation: relevant techniques and a benchmark framework
Mathematical Problems in Engineering, 2015

P. Campadelli, E. Casiraghi and C. Ceruti
Neighborhood Selection for Dimensionality Reduction
Image Analysis and Processing–ICIAP 2015

C. Ceruti, P. Campadelli and E. Casiraghi
Linear Regularized Compression of Deep Convolutional Neural Networks
Image Analysis and Processing–ICIAP 2017

C. Ceruti, V. Cuculo, A. D'Amelio, G. Grossi and R. Lanzarotti
Taking the hidden route: deep mapping of affect via 3D neural networks
Image Analysis and Processing–ICIAP 2017

Projects

A MATLAB implementation of the intrinsic dimensionality estimation techniques described by the articles in the publications section is available here

An R implementation is also available here by Kerstin Johnsson.

Teaching

aa 2016/2017 -- Visione Artificiale (Dip. Informatica, Unimi)
aa 2015/2016 -- Laboratorio di Informatica (Dip. Fisica, Unimi)
aa 2015/2016 -- Laboratorio di Programmazione 2 (Dip. Matematica, Unimi)
aa 2014/2015 -- Laboratorio di Informatica (Dip. Fisica, Unimi)
aa 2014/2015 -- Laboratorio di Programmazione 2 (Dip. Matematica, Unimi)
aa 2013/2014 -- Laboratorio di Informatica (Dip. Fisica, Unimi)
aa 2012/2013 -- Informatica di base (Dip. Farmacia, Unimi)
aa 2012/2013 -- Laboratorio di programmazione 1 (Dip. Matematica, Unimi)
aa 2012/2013 -- Laboratorio di Informatica (Dip. Fisica, Unimi)
aa 2011/2012 -- Minimat (Facoltà di Scienze e Tecnologie)
aa 2011/2012 -- Informatica di base (Dip. Biologia, Unimi)
aa 2010/2011 -- Laboratorio di programmazione 1 (Dip. Informatica, Unimi)

Links

My profile on Google Scholar