Scheda programma d'esame
INTELLIGENT SYSTEMS FOR PATTERN RECOGNITION
DAVIDE BACCIU
Academic year2023/24
CourseCOMPUTER SCIENCE
Code760AA
Credits9
PeriodSemester 2
LanguageEnglish

ModulesAreaTypeHoursTeacher(s)
INTELLIGENT SYSTEMS FOR PATTERN RECOGNITIONINF/01LEZIONI72
DAVIDE BACCIU unimap
Learning outcomes
Knowledge

The course introduces students to the analysis and design of advanced machine learning and deep learning models for modern pattern recognition problems and discusses how to realize advanced applications exploiting computational intelligence techniques. The course also presents fundamentals of signal and image processing. Particular focus will be given to pattern recognition problems and models dealing with sequential and time-series data.

The course is targeted at students who are pursuing specializations in Artificial Intelligence and Machine Learning, but it is of interest for data scientist and information retrieval specialists, roboticists and those with a bioinformatics curricula.

Assessment criteria of knowledge

Course examination for students attending the lectures is performed in 2 stages: midterm assignments and an oral presentation. Midterms waive the final project.

Midterm Assignment

Midterm assignments consist in a very short presentation (5 minutes per person) to be given in front of the class, presenting the key/most-interesting aspects of one of the following tasks:

  • A quick and dirty (but working) implementation of a simple pattern recognition algorithm
  • A report concerning the experience of installing and running a demo application realized using available deep learning and machine learning libraries
  • A summary of a recent research paper on topics/models related to the course content.

Students might be given some amount of freedom in the choice of assignments, pending a reasonable choice of the topic. The assignments will roughly be scheduled every 1 month.

Oral Presentation

The oral examination will test knowledge of the course contents (models, algorithms and applications).

Non attending students

Working students and those not attending course lectures will deliver a final project making up for the missing midterms. They will be subject to an oral examination like attending students.  Contact the instructor by mail to arrange project topics and examination dates.

The final project concerns preparing a presentation on a topic relevant to the course content or the realization of a software implementing a non-trivial learning model and/or a PR application relevant for the course. The content of the final project will be discussed in front of the instructor and anybody interested during the oral examination. Students are expected to prepare slides for a 15 minutes presentation which should summarize the ideas, models and results in the report. The exposition should demonstrate a solid understanding of the main ideas in the report.

Skills

Students completing the course are expected

  • to gain in-depth knowledge of advanced topics of machine learning, pattern recognition, deep learning, reinforcement learning, understanding their theory and applications;
  • to be able to individually read, understand and discuss research works in the field;
  • to be able to implement pattern recognition applications, machine learning, deep learning models using state of the art libraries and tools;
  • to be able to make limited advancements and contributions to the research in the field.

 

Assessment criteria of skills

Students will be given both programming and reading assignments (as part of the midterm or as final projects) to assess their development and research understanding skills.

Prerequisites

Course prerequisites include

  • knowledge of machine learning fundamentals ("Machine Learning" course);
  • knowledge of elements of probability and statistics, calculus and optimization algorithms ("Computational mathematics for learning and data analysis" course).

 

Teaching methods

The official language of the course is English: all materials, references and books are in English. Lecture slides will be made available, together with suggested readings, on the course website.

 

Syllabus

The topics covered as part of the course include:

  • Bayesian learning
  • Undirected graphical model
  • Dynamic Bayesian networks
  • Fundamentals of deep learning (CNN, Autoencoders, DBN, gated recurrent networks, etc)
  • Deep learning for machine vision and signal processing
  • Generative deep learning (VAE, GANs, Diffusion, Explicit models, ...)
  • Advanced deep learning models (transformers,  Neural Turing Machines, Memory networks, etc)
  • Deep graph networks
  • Principles of reinforcement learning and deep reinforcement learning
  • Signal processing and time-series analysis
  • Image processing, filters and visual feature detectors
  • Pattern recognition applications: machine vision, bio-informatics, robotics, medical imaging, etc.
  • ML and deep learning libraries
Bibliography

The course does not have an official textbook covering all its contents. However, reference books covering parts of the course are listed at the bottom of this section (note that some of them have an electronic version freely available for download).

David Barber, Bayesian Reasoning and Machine Learning, Cambridge University Press

Ian Goodfellow and Yoshua Bengio and Aaron Courville , Deep Learning, MIT Press

Simon J.D. Prince, Understanding Deep Learning, MIT Press, 2023

 

Non-attending students info

Working students and those not attending course lectures will handle a final project and will also be subject to an oral examination including both an oral presentation of the project as well as an examination on the course program.

Assessment methods

Course examination for students attending the lectures is performed in two stages, including midterm assignments and an oral presentation. Midterms provide a waiver for the final project.

Updated: 02/12/2023 10:52