February 19-20, 2020
Modern machine learning (ML) is a key to develop intelligent systems and analyze data in science and engineering. Today it provides impressive results in many fields, enabling intelligent technologies such as artificial voice assistants, and smart services such as optimized energy consumption. ML systems are nowadays considered as one of the largest share of growing market.
While the amount of available tools and frameworks is becoming impressive, their effective application to real-world challenges require an appropriate expertise. However, most of ML methods leverage the same building blocks and share basic concepts. Therefore, key to applying machine learning lays in understanding the basic formulations, relating them with prototypical study cases, reasoning on the situations when they are most appropriate.
We here provide a modified version of the long-standing successful courses taught at the University of Genova and MIT, and focus on the fundamental methods of modern ML, providing participants with the knowledge needed to get started with ML. The sessions on theoretical and algorithmic aspects will be complemented by hands-on training using Jupyter notebooks. The participants will also have an opportunity for a face-to-face session with the instructors to discuss individually relevant ML challenges.
The course is organised jointly by Simula Consulting and Machine Learning Genova Center (MaLGa).
Learn how to formulate problems as machine learning tasks and to design effective solution strategies
Understand the fundamental machine learning concepts and methods
Obtain an overview of the main supervised and unsupervised learning algorithms, incl. neural networks, with analysis of their strengths and weaknesses
Explore Python/Jupyter notebooks and relevant libraries for machine learning
Obtain hands-on experience using real-life data and specific use cases, both with stationary and temporal extent
This course provides a better understanding of machine learning fundamentals and is tailored towards professionals with a technical competence and basic programming skills.
This course describes key concepts, algorithms, and practical knowledge to professionals who are starting, or need to brush up machine learning skills, and provides participants with core knowledge to succeed to the advanced level.
09:00-14:00 (4 hours): Theoretical classes with Jupyter notebooks
Introduction to ML
- classification and regression
- linear/non linear models: features maps/kernels and neural nets
- model and feature selection
- dimensionality reduction
14:00-17:00 (2.5 hours): Hands-on activity with Jupyter notebook: ML concepts
09:00-14:00 (4 hours): A case-study: time series
Introduction to the problem
Hands-on activity with Jupyter notebook
14:00-17:00 (3 hours): Face2face sessions with the instructors (up to 30 min per participant)
Nicoletta Noceti is an Assistant Professor in Computer Science at the University of Genova. Her research activity is mainly focused on the design and development of visual computing methods combining computer vision and machine learning for images and videos understanding, with applications to human-machine interaction, robotics, and Ambient Assisted Living. Recently, she has also been working on the analysis of time data, in the context of predictive maintenance for industrial applications.
She is currently co-instructor for machine and deep learning courses both at master level and at PhD level.
Francesca Odone is an Associate Professor in Computer Science at the University of Genova. Her research interests are in the fields of computer vision and machine learning, including multi-resolution signal processing, feature extraction, feature selection and data-driven representations for visual data. She has been involved in various research projects and acted as a scientific coordinator of technology transfer contracts with SMEs, large companies and hospitals. For over ten years she has taught courses on data science topics (mainly machine learning, signal and image processing, computer vision) both at master level and at PhD level.