About Me

I received the Laurea degree in computer science in 2013, at university of Padova, Italy, with thesis about the application of RBM-based model on sequential data. In January 2014 I started Ph.D. in computer science at department of mathematics at the same university under the supervision of Prof. Alessandro Sperduti.

My main research interest is correlated to Machine Learning and in particular Neural Networks, Deep Learning and Computational Neuroscience. Most of the research that I carried out up to now is about the application of Neural Network on complex structured data.

Member of IEEE CIS Task Force on Deep Learning

Recent Publications

Linear dynamical based models for sequential domains
Luca Pasa, Alessandro Sperduti, Peter Tino.
International Joint Conference on Neural Networks, IJCNN 2017
Abstract: The aim of the paper is to explore how models based on a linear dynamic can be used in order to perform a prediction task in sequential domains. In the literature, it has already been shown that Linear Dynamical Systems (LDSs) can be quite useful when dealing with sequence learning tasks. Our aim is to study whether it is possible to use LDSs as building blocks for constructing more complex and powerful models....More.

Ph.D. Thesis: Linear Models and Deep Learning: Learning In Sequential Domains
Author:Luca Pasa
Supervisor: Alessandro Sperduti
16/03/2017, Università Degli Studi di Padova
Go to complete Thesis
Ph.D. defense Presentation