Fundamentals of machine learning for computer vision
Keywords |
Classification |
Keyword |
CNAEF |
Informatics Sciences |
Instance: 2023/2024 - 1S
Cycles of Study/Courses
Acronym |
No. of Students |
Study Plan |
Curricular Years |
Credits UCN |
Credits ECTS |
Contact hours |
Total Time |
MVCOMP |
8 |
Syllabus |
1 |
- |
6 |
42 |
162 |
Teaching language
English
Objectives
The aim of the course is to present some of the topics which are at the core of modern Machine Learning, from fundamentals to state-of-the-art methods. Emphasis will be put both on the essential theory and on practical examples and lab projects. Each exercise has been carefully chosen to reinforce concepts explained in the lectures or to develop and generalize them in significant ways. Upon the successful conclusion of the course, students should have the:
- Ability to work in team, organization and planning
-Ability to analyze and synthesize knowledge.
-knowledge of the fundamentals of machine learning.
-Ability to develop simple machine learning systems depending on existing needs and apply the most appropriate technological tools.
-Acquire the learning skills that allow to continue studying in a way that will be largely self-directed or autonomous
Learning outcomes and competences
Upon the successful conclusion of the course, students should have the:
- Ability to work in team, organization and planning
-Ability to analyze and synthesize knowledge.
-knowledge of the fundamentals of machine learning.
-Ability to develop simple machine learning systems depending on existing needs and apply the most appropriate technological tools.
-Acquire the learning skills that allow to continue studying in a way that will be largely self-directed or autonomous
Working method
À distância
Program
1. Introduction to Learning Theory [Data driven process; Overfitting and generalization; Taxonomy of the Learning Settings; Taxonomy of the Learning Tools; Representation, Evaluation, Optimization]
2. Introduction to Linear Regression [Criterion (Evaluation); Normal Equation; The Least-Mean-Square (LMS) method; Steepest descent; Ridge and Lasso regression]
3. Generative Classifiers [Optimal Bayes decision; Gaussian based classifier (linear and quadratic);
Conditional Independence and Naïve Bayes classifier; Non-parametric density estimation: Parzen window method]
4. Non- Generative Classifiers [Logistic regression; Fisher Discriminant Analysis;]
Applications in computer vision
5. Model Selection and evaluation
6. Introduction to Neural Networks
7. Introduction to Support Vector Machines
Applications in computer vision
8. Unsupervised Learning – Clustering [Clustering algorithms; Kmeans, kmedoids, soft kmeans; Mixture of Gaussians; Manifold Learning (PCA, MDA, ISOMAP and LLE)]
Applications in computer vision
9. Introduction to models for sequential data
Applications in computer vision
Mandatory literature
NIPS, ICML, IJCAI, AAAI, ECML, CVPR, etc.; Artigos recentes das conferências e revistas de referência na área: NIPS, ICML, IJCAI, AAAI, ECML, CVPR, etc.
Sergios Theodoridis;
Machine Learning: A Bayesian and Optimization Perspective
Complementary Bibliography
Christopher M. Bishop;
Pattern recognition and machine learning. ISBN: 978-0-387-31073-2
Trevor Hastie;
The elements of statistical learning. ISBN: 0-387-95284-5
Teaching methods and learning activities
Participatory lectures, seminars and conferences, learning based on the resolution of practical cases and projects, autonomous work and independent study by students, group work and cooperative learning.
Subjects will be covered both in participatory lectures, where students will have the chance to implement methods for themselves. During the lecture part, the course topics will be presented and discussed. The practical/lab periods will be used for solving exercises and for the development of the assignments.
Students will be assigned weekly individual homework assignments during the whole duration of the course, involving exercises, readings and summarization of selected texts. They will account for 30% of the final grade. Practical work will consist of one project covering the course topics.
Evaluation Type
Distributed evaluation with final exam
Assessment Components
Designation |
Weight (%) |
Participação presencial |
35,00 |
Trabalho prático ou de projeto |
65,00 |
Total: |
100,00 |
Amount of time allocated to each course unit
Designation |
Time (hours) |
Estudo autónomo |
60,00 |
Frequência das aulas |
42,00 |
Trabalho escrito |
30,00 |
Trabalho laboratorial |
30,00 |
Total: |
162,00 |
Eligibility for exams
Students will be assigned weekly individual homework assignments during the whole duration of the course, involving exercises, readings and summarization of selected texts. Weekly assignments will have a weight of 30% in the final grade. The project work to be developed will consist of addressing a topic from the course and will have a weight of 65%.
Calculation formula of final grade
The components for student evaluation are: • H – Homeworks • P - Project.
Each component will receive a grading in 0-20.
The final score will be calculated according to the following rule: 35% * H+ 65% * P. Grading will be from 0 to 20.
A PASSing grade corresponds to a minimum of 10.