Instructors
Lorenzo Rosasco
University of Genova
(also Istituto Italiano di Tecnologia and Massachusetts Institute of Technology)
lorenzo [dot] rosasco [at] unige [dot] it
Machine Learning is a key to develop intelligent systems and analyze data in science and engineering. Machine Learning engines enable intelligent technologies such as Siri, Kinect or Google self driving car, to name a few. At the same time, Machine Learning methods help deciphering the information in our DNA and make sense of the flood of information gathered on the web, forming the basis of a new “Science of Data”. This course provides an introduction to the fundamental methods at the core of modern Machine Learning. It covers theoretical foundations as well as essential algorithms. Classes on theoretical and algorithmic aspects are complemented by practical lab sessions.
This introductory course is suitable for undergraduate/graduate students, as well as professionals.
Course Structure:
The course started in 2013 has seen an increasing national and international attendance over the years with a peak of over 100 participants in 2015.
Important dates:
Registration fee (note):
Related courses:
Classes will take place at the Department of Informatics Bioengineering Robotics and Systems Engineering (DIBRIS) of the University of Genova in Via Dodecaneso 35, 16146 Genova. See here for directions and travelling information
Genova is in the region of Liguria in the Italian Riviera (see here or here for some nice pics and a video).
Here you can find a list of hotels near the department (~ 20' walk) or in the city centre (~20' by bus).
Here is a list of places where you can go for lunch. And here is a link to the online map.
For more info write to:
vigogna [at] dibris [dot] unige [dot] it
cristian [dot] rusu [at] iit [dot] it
raffaello [dot] camoriano [at] iit [dot] it
University of Genova
(also Istituto Italiano di Tecnologia and Massachusetts Institute of Technology)
lorenzo [dot] rosasco [at] unige [dot] it
EURECOM
Drawing meaningful conclusions on the way complex real life phenomena work and being able to predict the behavior of systems of interest require developing accurate and highly interpretable mathematical models whose parameters need to be estimated from observations. In modern applications, however, we are often challenged with the lack of such models, and even when these are available they are too computational demanding to be suitable for standard parameter optimization/inference methods.
This tutorial will introduce probabilistic models based on Gaussian processes as attractive tools to tackle these challenges in a principled way and to allow for a sound quantification of uncertainty. The tutorial will formally define Gaussian processes starting from the formulation of Bayesian linear models with infinite basis functions, and draw connections with non-probabilistic kernel machines and deep neural networks.
Carrying out inference for Gaussian processes poses huge computational challenges that arguably hinder their wide adoption. In recent years, however, have been a considerable amount of novel contributions that are allowing Gaussian processes to be applied to problems at an unprecedented scale and to new areas where uncertainty quantification is of fundamental importance. This tutorial will expose attendees to such recent advances, trends and challenges in Gaussian process modeling and inference, and stimulate the debate about the role of Gaussian process models in solving complex modern machine-learning tasks where deep neural networks are currently the preferred choice.
Gatsby Computational Neuroscience Unit
Generative models of images have made an extraordinary amount of progress over the past five years, moving from vaguely plausible images of handwritten digit to nearly-photorealistic pictures of imaginary people. This tutorial will cover the key line of work, generative adversarial networks and their variants. We will discuss the original algorithm, theoretical issues with its foundations, and various approaches to resolving them, including the Wasserstein GAN and recent kernel-based improvements.
| CLASS | DAY | TIME | SUBJECT | FILES |
| 1 | 06/17 | 9:30 - 11:00 | Introduction to Machine Learning | |
| 2 | 06/17 | 11:30 - 13:00 | Local Methods and Model Selection | |
| 3 | 06/17 | 14:00 - 16:00 | Laboratory 1: Local Methods for Classification | |
| 4 | 06/18 | 9:30 - 11:00 | Regularization Networks I: Linear Models | |
| 5 | 06/18 | 11:30 - 13:00 | Regularization Networks II: Kernels | |
| 6 | 06/18 | 14:00 - 16:00 | Laboratory 2: Regularization Networks | |
| Tutorial | 06/19 | 9:30 - 11:00 | Maurizio Filippone - Introduction to Gaussian Processes | |
| Tutorial | 06/19 | 11:30 - 13:00 | Dougal Sutherland - Adversarial generative models of images | |
| - | 06/19 | Afternoon | Free | |
| 7 | 06/20 | 9:30 - 11:00 | Dimensionality Reduction and PCA | |
| 8 | 06/20 | 11:30 - 13:00 | Variable Selection and Sparsity | |
| 9 | 06/20 | 14:00 - 16:00 | Laboratory 3: PCA and Sparsity | |
| 10 | 06/21 | 9:30 - 11:00 | Clustering | |
| 11 | 06/21 | 11:30 - 13:00 | Data Representation: Deep Learning |
University of Genova (UNIGE)
Laboratory for Computational and Statistical Learning (LCSL)
vigogna [at] dibris [dot] unige [dot] it
Istituto Italiano di Tecnologia (IIT)
Laboratory for Computational and Statistical Learning (LCSL)
cristian [dot] rusu [at] iit [dot] it
Istituto Italiano di Tecnologia (IIT)
Laboratory for Computational and Statistical Learning (LCSL)
raffaello [dot] camoriano [at] iit [dot] it