Informazioni in aggiornamento fino al 30/06/2026 CODICE 86928 ANNO ACCADEMICO 2026/2027 CFU 5 cfu anno 1 ROBOTICS ENGINEERING 11963 (LM-32) - GENOVA SETTORE SCIENTIFICO DISCIPLINARE INFO-01/A LINGUA Inglese SEDE GENOVA PERIODO 1° Semestre MATERIALE DIDATTICO AULAWEB PRESENTAZIONE The goal of the Machine Learning module is both to provide the basics of machine learning and pattern recognition theory and to expose the student to machine learning methods, workflows, and best practices, with emphasis on applications in Robotics and a focus on artificial neural networks as well as several other techniques. OBIETTIVI E CONTENUTI OBIETTIVI FORMATIVI L'insegnamento introduce le basi del Machine Learning e delle Artificial Neural Networks, così come altre tecniche ben note per la risoluzione di problemi di apprendimento supervisionato e non supervisionato, con particolare enfasi sulle applicazioni in ambito Robotics. Tali sistemi di apprendimento possono essere applicati al riconoscimento di pattern, all’approssimazione di funzioni, alla previsione di serie temporali e a problemi di clustering. Sarà inoltre fatto cenno all’uso delle Artificial Neural Networks come sistemi statici per la codifica dell’informazione e come sistemi dinamici per l’ottimizzazione e l’identificazione. OBIETTIVI FORMATIVI (DETTAGLIO) E RISULTATI DI APPRENDIMENTO After successfully attending the course, the student will be able to: demonstrate knowledge of a range of techniques and problems in machine learning and pattern recognition, including the underlying scientific and technical rationale apply selected techniques to relevant problems code simple and medium-complexity machine learning methods using standard programming tools, without being limited to using software libraries know the basics of popular machine learning libraries that enable the use of more powerful pre-trained methods tackle the workflow of a machine learning assignment from data wrangling to result presentation use critical thinking to analyse a problem and select the appropriate machine learning method to apply PREREQUISITI Basic multi-dimensional calculus Continuous optimization Probability and some information theory Discrete proficiency in programming (one of Matlab or Python, or ability to quickly catch up if coming from different programming backgrounds) MODALITA' DIDATTICHE Lectures Practical assignments, formatted as homeworks but also worked out with assistance by the teacher during lab hours, to be handed in every 2 weeks Assignments are used for continuous assessment whose weight is 50% of the final marks, the rest being obtained with a final exam and discussion. Due to the teaching style and to the continuous assessment, attendance is mandatory PROGRAMMA/CONTENUTO Introduction Perceptual problems The decision problem in the presence of complete deterministic information: Representation problems The decision problem in the presence of complete probabilistic information: Bayes decision theory The decision problem in the presence of incomplete samples (data): Statistics and the learning problem. Inductive bias, the bias-variance dilemma Parametric methods and maximum likelihood estimation Non-parametric methods, some popular classification and clustering methods Evaluating learning: Indexes and resampling methods. Neural networks: Historical methods, shallow networks The learning problem as optimization. Algorithms and strategies. Data mapping: Dimensionality reduction and kernel methods Deep neural networks Learning from sequential data TESTI/BIBLIOGRAFIA Course slides and assignments are available on the official study portal. A selection of suggested readings (journal articles and textbooks) will be provided during lectures. DOCENTI E COMMISSIONI STEFANO ROVETTA Ricevimento: A disposizione per 20 minuti dopo ciascuna lezione Su appuntamento. Dato che il docente insegna in diversi corsi, in caso di contatto non di persona (email, messaggistica Teams, messaggistica Aulaweb...) è necessario indicare a quale corso di laurea e insegnamento ci si riferisce. LEZIONI INIZIO LEZIONI https://corsi.unige.it/10635/p/studenti-orario Orari delle lezioni L'orario di questo insegnamento è consultabile all'indirizzo: Portale EasyAcademy ESAMI MODALITA' D'ESAME Oral or quiz MODALITA' DI ACCERTAMENTO The final exam consists either in an interview with technical questions and exercises, and in the discussion of the assignments, or alternatively in a quiz with short questions on the same topics and a report discussing the assignments. Final marks given 50% by continuous assessment and 50% by exam. ALTRE INFORMAZIONI About 30 hours of lectures and 18 hours of assignments / guided exercises.
