OVERVIEW

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.

AIMS AND CONTENT

LEARNING OUTCOMES

The course introduces the basics of Machine Learning and Artificial Neural Networks, as well as other well-known techniques for solving supervised and unsupervised learning problems, with a specific emphasis on Robotics applications. Such learning systems can be applied to pattern recognition, function approximation, time-series prediction and clustering problems. Some mention will be made to the use of ANNs as static systems for information coding, and dynamical systems for optimization and identification.

AIMS AND LEARNING OUTCOMES

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
• 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

PREREQUISITES

• 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)

TEACHING METHODS

• 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.

SYLLABUS/CONTENT

1. Introduction
2. Perceptual problems
3. The decision problem in the presence of complete deterministic information: Representation problems
4. The decision problem in the presence of complete probabilistic information: Bayes decision theory
5. The decision problem in the presence of incomplete samples (data): Statistics and the learning problem. Inductive bias, the bias-variance dilemma
6. Parametric methods and maximum likelihood estimation
7. Non-parametric methods, some popular classification and clustering methods
8. Evaluating learning: Indexes and resampling methods.
9. Neural networks: Historical methods, shallow networks
10. The learning problem as optimization. Algorithms and strategies.
11. Data mapping: Dimensionality reduction and kernel methods 
12. Deep neural networks
13. Learning from sequential data

RECOMMENDED READING/BIBLIOGRAPHY

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.

TEACHERS AND EXAM BOARD

Exam Board

STEFANO ROVETTA (President)

FRANCESCO MASULLI

RENATO UGO RAFFAELE ZACCARIA

ARMANDO TACCHELLA (President Substitute)

LESSONS

LESSONS START

https://corsi.unige.it/10635/p/studenti-orario

Class schedule

The timetable for this course is available here: Portale EasyAcademy

EXAMS

EXAM DESCRIPTION

The exam consists of (1) evaluation of assignments and a summary report, and (2) a written quiz.

Assignments must have been uploaded within the required deadlines during the first semester. The course cannot be attended during the second semester.

ASSESSMENT METHODS

Evaluation of homeworks

Homeworks address the following learning outcomes:

• 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
• tackle the workflow of a machine learning assignment from data wrangling to result presentation

Quiz grading

Quizzes address the following learning outcomes:

• demonstrate knowledge of a range of techniques and problems in machine learning and pattern recognition, including the underlying scientific and technical rationale
• use critical thinking to analyse a problem and select the appropriate machine learning method to apply

Exam schedule

FURTHER INFORMATION

About 30 hours of lectures and 18 hours of assignments / guided exercises.