Identifying Data 2020/21
Subject (*) Advanced Machine Learning for Computer Vision Code 614535008
Study programme
Máster Universitario en Visión por Computador
Descriptors Cycle Period Year Type Credits
Official Master's Degree 2nd four-month period
 First Obligatory 6
Language
English
Teaching method Hybrid
Prerequisites
Department Ciencias da Computación e Tecnoloxías da Información
Coordinador
Rouco Maseda, Jose
 E-mail
jose.rouco@udc.es
Lecturers
Novo Bujan, Jorge
Rouco Maseda, Jose
 E-mail
j.novo@udc.es
jose.rouco@udc.es
Web
General description O obxectivo desta materia é coñecer e aplicar modelos neuronais avanzados, coñecer as técnicas da estado da arte de aprendizaxe profunda, con formulacións de adestramento end-to-end, e minimizando el uso de datos etiquetados, para resolver aplicacións de visión por computador usando as metodoloxías cubertas na materia.
Contingency plan 1. Modificacións nos contidos

Sen cambios

2. Metodoloxías

Mantéñense todas as actividades. O ensino será telemático e as clases desenvolveranse sincrónicamente no horario oficial de clases. Pode ser que, por razóns de sobrevidas, algunhas das clases se realicen de forma asincrónica, o que se lle comunicará ao alumnado con anticipación.

3. Mecanismos de atención personalizada ao alumnado

As titorias serán telemáticas e requirirán cita previa.

4. Modificacións na avaliación

Sen cambios na avaliación. As actividades de avaliación que non se poidan levar a cabo en persoa, realizaránse telemáticamente a través das ferramentas institucionais en Office 365 e Moodle. Neste caso, requirirase a adopción dunha serie de medidas de validación que requirirán que o alumnado teña un dispositivo cun micrófono e unha cámara, mentres non se dispoña dun software de validación axeitado. Pódese concertar unha entrevista con cada estudante para comentar ou explicar parte ou a totalidade das probas realizadas. Nestes escenarios, poderán modificarse algunhas das actividades plantexadas en cada epígrafe, adaptándoas á situación, pero non a súa contribución xeral á cualificación final (a porcentaxe de ponderación)

5. Modificacións da bibliografía ou webgrafía

Sen cambios

Study programme competencies
Code Study programme competences
A2 CE2 - To know and apply machine learning and pattern recognition techniques applied to computer vision
B1 CB6 - To possess and understand knowledge that provides a basis or opportunity to be original in the development and/or application of ideas, often in a research context
B2 CB7 - That students are able to apply their acquired knowledge and problem-solving skills in new or unfamiliar environments within broader (or multidisciplinary) contexts related to their area of study
B5 CB10 - That students possess the learning skills to enable them to continue studying in a largely self-directed or autonomous manner
B6 CG1 - Ability to analyze and synthesize knowledge
B8 CG3 - Ability to develop computer vision systems depending on existing needs and apply the most appropriate technological tools
B10 CG5 - Ability to identify unsolved problems and provide innovative solutions
B11 CG6 - Ability to identify theoretical results or new technologies with innovative potential and convert them into products and services useful to society
C1 CT1 - Practice the profession with a clear awareness of its human, economic, legal and ethical dimensions and with a clear commitment to quality and continuous improvement
C2 CT2 - Ability to work as a team, organize and plan

Learning aims
Learning outcomes Study programme competences
To know, apply and evaluate advanced neural models. AC2
 BC1
BC2
BC5
BC6
BC8
BC10
BC11
 CC1
CC2
To know deep learning techniques, with end-to-end training approaches, and minimizing the use of tagged data. AC2
 BC1
BC2
BC5
BC6
BC8
BC10
BC11
 CC1
CC2
To solve computer vision applications using advanced machine learning methods. AC2
 BC1
BC2
BC5
BC6
BC8
BC10
BC11
 CC1
CC2

Contents
Topic Sub-topic
Multilayer perception and backpropagation.
Convolutional and recurrent networks
Principles of deep learning
Self-supervised learning and autoencoders
Advanced neural models for computer vision.
Advanced supervised learning paradigms
Selected topics in machine learning for computer vision
Advanced applications in computer vision.

Planning
Methodologies / tests Competencies Ordinary class hours Student’s personal work hours Total hours
Guest lecture / keynote speech A2 B1 B2 B5 B6 B8 B10 B11 C2 C1 10 20 30
Case study A2 B1 B2 B5 B6 B8 B10 B11 C1 C2 4 16 20
Objective test A2 B1 B2 B5 B6 B8 B10 B11 C1 C2 2 0 2
Laboratory practice A2 B1 B2 B5 B6 B8 B10 B11 C1 C2 16 32 48
Research (Research project) A2 B1 B2 B5 B6 B8 B10 B11 C2 C1 10 40 50
 
Personalized attention 0 0 0
 
(*)The information in the planning table is for guidance only and does not take into account the heterogeneity of the students.

Methodologies
Methodologies Description
Guest lecture / keynote speech Participatory lessons with the aim of learning the theoretical content of the subject
Case study Elaboration and presentation of selected state-of-the-art methodologies related to the subject.
Objective test Continuous evaluation tests during the course. Evaluation by examination at the end of the course as an alternative.
Laboratory practice Analysis and resolution of practical cases with the aim of strengthening the practical application of the theoretical content. Practice in computer classrooms, learning based on the resolution of practical cases, autonomous work and independent study of the students, and group work and cooperative learning.
Research (Research project) Learning based on the resolution of practical cases, autonomous work and independent study of the students, and group work and cooperative learning.

Personalized attention
Methodologies
Research (Research project)
Case study
Laboratory practice
Description
< br>Resolution of doubts during laboratory practices. Individualized advice during research projects and case studies.

Assessment
Methodologies Competencies Description Qualification
Research (Research project) A2 B1 B2 B5 B6 B8 B10 B11 C2 C1 Resolution of practical cases of application of the subject through autonomous work of the student, and using the techniques learned during the course 20
Case study A2 B1 B2 B5 B6 B8 B10 B11 C1 C2 Elaboration and presentation of works on selected state-of-the-art methodologies 15
Laboratory practice A2 B1 B2 B5 B6 B8 B10 B11 C1 C2 Analysis and resolution of practical cases with the aim of strengthening the practical application of theoretical content 40
Objective test A2 B1 B2 B5 B6 B8 B10 B11 C1 C2 Continuous evaluation tests during the course. Evaluation by examination at the end of the course as an alternative 25
 
Assessment comments

The evaluation corresponding to the objective test may be passed by
means of the tests scheduled during the course or by means of the final
exam.

Sources of information
Basic

Complementary
  • Ian Goodfellow, Yoshua Bengio, Aaron Courville. Deep Learning. MIT Press. 2017.

  • Recent papers from relevant scientific journals and conferences: NIPS, ICML, IJCAI, AAAI, ECML, CVPR, ICDM, IEEE PAMI, IEEE TKDE, etc.

Recommendations
Subjects that it is recommended to have taken before
Fundamentals of Machine Learning for Computer Vision /614535007
Image Description and Modeling/614535004

Subjects that are recommended to be taken simultaneously
Visual Recognition/614535005

Subjects that continue the syllabus

Other comments


(*)The teaching guide is the document in which the URV publishes the information about all its courses. It is a public document and cannot be modified. Only in exceptional cases can it be revised by the competent agent or duly revised so that it is in line with current legislation.