Machine learning explores the study and construction of algorithms that can learn from and make predictions on data. Such algorithms operate by building a model from example inputs in order to make data-driven predictions or decisions, rather than following strictly static program instructions. Machine learning algorithms can be applied to virtually any scientific and non-scientific field (health, security and cyber-security, management, finance, automation, robotics, marketing..)
The course is taught in English. Attending classes is HIGHLY recommended (homeworks, mid-term, laboratory)
Homeworks and self-assessment tests are distributed via the google group, you MUST register
Summary of Course Topics
The course introduces motivations, paradigms and applications of machine learning.
Supervised learning: decision trees, instance-based learning, naīve Bayes, support vector machine, neural networks, deep learning, ensamble methods. Unsupervised learning: clustering. Semi-supervised learning. Reinforcement learning. Genetic algorithms and genetic programming. Issues in machine learning: underfitting, overfitting, model selection, error analysis.
Students will experiment the main algorithms using the Weka ML software Weka. Part of the experimental work is done in class, therefore students must install Weka and bring their labtops in class. Except for the first lesson, any other lesson consists in the presentation of a ML algorithm and the subsequent experimentation on WEKA.
Detailed description of the experiments in each lab will be handled every week during the course.
Tom Mitchell, Machine Learning, McGraw-Hill, 1997 (updated material is continuously added)
Project 2016 (Spring): GAME WINNER PREDICTION CONTEST
The spring 2016 project was be a competion among student teams (max 3 students per team). The task is to predict the winner of a Role Playing Game (RPG) with direct clash. Students will be given a large dataset with detailed information on thousands of games, including the ID of the two competitors, the date of the match and the winner ID. The students will deliver the Predictor by the end of June (according to precise project specifications). Instructors will feed the systems with the details of additional games (not in the learning set) and compute the precision of each system at predicting the winner ID.
The project description is found here
The learning dataset coun be downloaded here
Weka project 2015
Students will select a machine learning project of their choice and use one or more algorithms to solve the selected problem. A good project is such if 1)It is possible to obtain a dataset (either because available or because it can be built) and sufficient information concerning the problem 2)The representation of domain instances (objects relevant for the problem being considered) is not trivial (= sufficiently large number of features, sufficiently large number of values or real-valued features) 3) There is a performance evaluation and 4) (Not strictly necessary but suggested): To solve the problem , students need to learn something new and interdisciplinary
How a project is evaluated:
Simple problem, easy-to-model easy-to-describe instances, small dataset, standard ML learning algorithms using WEKA: up to 25/30
Simple problem, easy-to-model easy-to-describe instances, medium-large datset, some complex algorithm not in weka or a more efficient implementation of existing algorithm (e.g. some ad-hoc software developed): up to 28
Original problem, complex dataset, not straightforward use of algorithms or new algorithm or ad-hoc implementation: up to 30 L