Section outline

  • Intelligent Systems for Pattern Recognition - 9 CFU

    Collapse all Expand all

    Code: 760AA, Credits (ECTS): 9, Semester: 2, Official Language: English

    Instructor: Davide Bacciu 

    Contact: email - phone 050 2212749

    Office: Room 331, Dipartimento di Informatica, Largo B. Pontecorvo 3, Pisa

    Office Hours: (email to arrange meeting)

  • Course Information

    The course is held on the second term. The schedule for A.Y. 2024/25 is provided in table below.

    The first lecture of the course will be ON FEBRUARY 18th 2025 h. 11.00. The course will be hybrid, both in person and online on the dedicated MS Team.

    Recordings of the lectures will be made available to the students following the course.

    Day Time
    Tuesday 11.15-13.00 (Room C1)
    Wednesday 16.15-18.00 (Room E)
    Thursday 14.15-16.00 (Room E)

     

    Objectives

    Course Prerequisites

    Course prerequisites include knowledge of machine learning fundamentals (e.g. covered through ML course). Knowledge of elements of probability and statistics, calculus and optimization algorithms are also expected. Previous programming experience with Python is a plus for the practical lectures.

    Course Overview

    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 is articulated in five parts. The first part introduces basic concepts and algorithms concerning traditional pattern recognition, in particular as pertains sequence and image analysis. The next two parts introduce advanced models from two major learning paradigms, that are deep neural networks and probabilistic models and their use in pattern recognition applications. The fourth part will cover generative deep learning and the intersection between probabilistic and neural models. The final part of the course will present selected recent works, advanced models and applications of learning models.

    Presentation of the theoretical models and associated algorithms will be complemented by introductory classes on the most popular software libraries used to implement them.

    The course hosts guest seminars by national and international researchers working on the field as well as by companies that are engaged in the development of advanced applications using machine learning models.

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

    Topics covered -Bayesian learning, graphical models, learning with sampling and variational approximations, fundamentals of deep learning (CNNs, AE, DBN, GRNs), deep learning for machine vision and signal processing, advanced deep learning models (transformers, foundational models, NTMs), generative deep learning (VAE, GANs, diffusion models, score-based models) deep graph networks, 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), introduction to programming libraries and frameworks.

    Textbooks and Teaching Materials

    We will use two main textbooks, one covering the parts about generative and probabilistic models, and the other covering the deep learning modules. Note that all books have an electronic version freely available online.

    BOOKS

    [BRML] David Barber, Bayesian Reasoning and Machine Learning, Cambridge University Press (PDF)

    [SD] Simon J.D. Prince, Understanding Deep Learning, MIT Press (2023) (PDF)

  • Introduction (2h)

    Introduction to the course philosophy, its learning goals and expected outcomes. We will discuss prospectively the overall structure of the course and the interelations between its parts. Exam modalities and schedule are also discussed (for both M.Sc. and Ph.D. students).

      Date Topic  References    Additional Material 
    1 18/02/2025
    (11-13)    		 Introduction to the course
    Motivations and aim; course housekeeping (exams, timetable, materials); introduction to modern pattern recognition applications    		    

  • Fundamentals of Pattern Recognition (6h)

    The module will provide a brief introduction to classical pattern recognition for signal/timeseries and for images. We will cover approaches working on the spatial (temporal) and frequency (spectral) domain, presenting methods to represent temporal and visual information in static descriptors, as well as approaches to identify relevant patterns in the data (feature descriptors). Methodologies covered include correlation analysis, Fourier analysis, wavelets, intensity gradient-based descriptors and detectors, normalized cut segmentation.

      Date Topic  References    Additional Material 
    2 19/02/2025
    (16-18)    		 Signal processing
    Timeseries; time domain analysis (statistics, correlation); spectral analysis; fourier analysis.     		   
    3 20/02/2025
    (14-16)    		 Image Processing I
    Spatial feature descriptors (color histograms, SIFT); spectral analysis.     		 

     Additional readings:
     [1] Survey on visual descriptors

    Software:

    A tweakable and fast implementation of SIFT in C (on top of OpenCV)
    4 25/02/2025
    (11-13)    		 Image Processing II
     Feature detectors (edge, blobs); image segmentation;
    		  Additional readings 
    [2] Survey on visual feature detectors

    A reference book for the pattern recognition part is " S. THEODORIDIS, K. KOUTROUMBAS, Pattern Recognition, 4th edition". It is not needed for the sake of the course, but it is a reference book if you are interested on the topic. It is not available online for free (legally; what you do with Google is none of my business).

    You can find the original NCUT paper freely available from authors here.
    4b 25/02/2025
    (11-13)    		 Image Processing III
     Wavelet decompositions    		    

  • Probabilistic (Generative) Learning (30h)

    The module introduces probabilistic learning, causal models, generative modelling and Bayesian learning. We will discuss fundamental algoritms and concepts, including Expectation-Maximization, sampling and variational approximations, and we will study relevant models from the three fundamental paradigms of probabilistic learning, namely Bayesian networks, Markov networks and dynamic models.  Models covered include: Bayesian Networks, Hidden Markov Models, Markov Random Fields, Boltzmann Machines,  Latent topic models.

      Date Topic  References   Additional Material 
      5  26/02/2025
    (16-18)    		 Introduction to Generative Graphical Models I
    P    robability refresher    		 [BRML] Ch. 1 and 2 (Refresher)  
    6 27/02/2025
    (14-16)    		 Introduction to Generative Graphical Models II
    G    raphical model representation; directed and undirected models    		 [BRML] Sect. 3.1, 3.2 and 3.3.1
    (conditional independence)    		 Software
    • Pyro - Python library based on PyTorch
    • PyMC3 - Python library based on Theano
    • Edward - Python library based on TensorFlow
    • TensorFlow Probability - Probabilistic models and deep learning in Tensorflow
    7 04/03/2025
    (11-13)

    Conditional Independence: Representation and Learning - Part I
    Bayesian networks; representing joint distributions; conditional independence;

    Guest lecture by Riccardo Massidda

    		 [BRML] Sect. 3.3 (Directed Models and conditional independence)   
      05/03/2025
    (16-18)    		 LECTURE CANCELLED DUE TO STUDENT ASSEMBLY    
    8 06/03/2025
    (14-16)

    Conditional Independence: Representation and Learning - Part II
    d-separation; Markov properties; faithfulness; Markov models

    Guest lecture by Riccardo Massidda

    		 [BRML] Sect. 4.1, 4.2.0-4.2.2 (Undirected Models and Markov Properties) 
    [BRML] Sect. 4.5 (Expressiveness)    		  
    9 11/03/2025
    (11-13)

    Graphical Causal Models 

    causation and correlation; causal Bayesian networks; structural causal models; causal Inference

    Guest lecture by Riccardo Massidda

    Barber's book is minimal on causality (only Section 3.4). My suggestions is that you complement the content of the slides (which is sufficient for the exam) with reading from this book, namely:

    -Chapters 2 & 3 (high level introduction to causality)

    - Sections 6.1-6.5 (more technical discussion on lecture content) 

    		 f you are interested in deepening of your knowledge on causality this is an excellent book (also freely available online): Jonas Peters, Dominik Janzing, Bernhard Schölkopf, Elements of causal inference : foundations and learning algorithms, MIT Press
    10 12/03/2025
    (16-18)

    Structure Learning and Causal Discovery 

    constraint-based methods; score-based methods;
    parametric assumptions 

    Guest lecture by Riccardo Massidda

    		 [BRML] Sect. 9.5.1 (PC algorithm)
    [BRML] Sect. 9.5.2 (Independence testing)
    [BRML] Sect. 9.5.3 (Structure scoring)

    Additional readings
    [3] A short review of BN structure learning
    [4] PC algorithm with consistent ordering for large scale data
    [5] MMHC - Hybrid structure learning algorithm

    Software
    - A selection of BN structure learning libraries in Python: pgmpy, bnlearn, pomegranate.
    - bnlearn: the most consolidated and efficient library for BN structure learning (in R)
    - Causal learner: a mixed R-Matlab package integrating over 26 BN structure learning algorithms.
    11 13/03/2025
    (14-16)    		 Hidden Markov Models  - Part I
    learning in directed graphical models;  generative models for sequential data; hidden/latent variables; inference problems on sequential data    		 [BRML] Sect. 23.1.0 (Markov Models)  Additional Readings
    [6]  A classical tutorial introduction to HMMs
      14/03/2025
    (14-16)    		 RECOVERY LECTURE CANCELLED DUE TO HYDROLOGICAL RISK    
    12 18/03/2025
    (09-11)

    Hidden Markov Models - Part II
    forward-backward algorithm;  learning as inference; EM algorithm

    [BRML] Sect. 23.2.0-23.2.4 (HMM and forward backward) 

    [BRML] Sect. 23.3.1-23.3.4 (EM and learning)

    		  
    13 19/03/2025
    (14-16)    		 Hidden Markov Models - Part III
    Viterbi algorithm; dynamic bayesian networks    		 [BRML] Sect. 23.2.6 (Viterbi)  
             

  • Course Grading and Exams

    Typical course examination (for students attending the lectures) is performed in 2 stages: midterm assignments and an oral exam. Midterms waive the final project.

    Midterm Assignment

    Midterms consist in short assignments involving with 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.

    The midterms can consist in either the delivery of code (e.g. colab notebook) or a short slide deck (no more than 10 slides) presenting the key/most-interesting aspects of the assignment. 

    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 3/4 weeks.

    Oral Exam

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

    Exam Grading (with Midterms)

    The final exam vote is given by the oral grade. The midterms only wave the final project but do not contribute to the grade. In other words you can only fail or pass a midterm. You need to pass all midterms in order to succesfully wave the final project.

    Alternative Exam Modality (No Midterms / Non attending students)

    Working students, those not attending lectures, those who have failed midterms or simply do not wish to do them, can complete the course by delivering a final project and an oral exam.  Final project topics will be released in the final weeks of the course: contact the instructor by mail to arrange choice of the topics once these are published.

    The final project concerns preparing a report 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.

    Grade for this exam modality is determined as

     \( G = 0.5 \cdot (G_P + G_O) \)

    where \( G_P \in [1,30] \) is the project grade and \( G_O \in [1,32] \) is the oral grade

  • Midterms and Projects

  • Bibliography

    1. Scott Krigg, Interest Point Detector and Feature Descriptor Survey, Computer Vision Metrics, pp 217-282, Open Access Chapter
    2. Tinne Tuytelaars and Krystian Mikolajczyk, Local Invariant Feature Detectors: A Survey, Foundations and Trends in Computer Graphics and Vision, Vol. 3, No. 3 (2007) 177–2, Online Version
    3. C. Glymour, Kun Zhang and P. Spirtes, Review of Causal Discovery Methods Based on Graphical Models Front. Genet. 2019, Online version
    4. Bacciu, D., Etchells, T. A., Lisboa, P. J., & Whittaker, J. (2013). Efficient identification of independence networks using mutual information. Computational Statistics, 28(2), 621-646, Online version
    5. Tsamardinos, I., Brown, L.E. & Aliferis, C.F. The max-min hill-climbing Bayesian network structure learning algorithm. Mach Learn 65, 31–78 (2006), Online version
    6. Lawrence R. Rabiner. A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 1989, pages 257-286, Online Version