Anar al contingut (clic a Intro)
UdG Home UdG Home
Tancar
Menú

Estudia

General information

Academic year:
2024
Description:
The aim of this course is to deepen in the knowledge of Machine Learning by studying different advanded techniques and applications of data science 1. Deep learning 2. Transfer learning 3. Reinforcement learning 4. Convolutional networks for image processing 5. Text mining. Natural language processing 6. Recommender systems
Academic credits:
6
Course coordinator:
Narcis Palomeras Rovira

Groups

Group A

Duration:
One-semester, 1st semester
Teaching staff:
Hayat Hussein Rajani
Language of the classes:
English (100%)

Competences

  • CG4- Designing creative proposals
  • CB6- Possess and understand the knowledge that provides a basis or opportunity to be original in the development and/or application of ideas, often in a research context
  • CB7- That students know how to apply the knowledge acquired and their ability to solve problems in new or unfamiliar environments within broader contexts related to their area of ??study
  • CB10- That students have the learning skills to allow them to continue studying in a way that will mostly be self-directed or autonomous
  • CE1- Programming, at an advanced level, in the languages and libraries most used in intelligent field robotics
  • CE2- Analyse a problem related to intelligent autonomous systems and identify the appropriate techniques and tools to solve it
  • CE3- Understand, develop, modify and effectively apply machine learning methods.
  • CE8- Understand the mathematical foundations of intelligent robotic system algorithms

Syllabus

1. Introduction

2. Learning Paradigms

3. Deep Learning Applications

4. Adversarial Training

5. Long Short-Term Memory in Computer Vision

6. Topics on Historical Neutral Networks

Activities

Activity type Hours with a teacher Hours without a teacher Virtual hours with a teacher Total
Assessment test 5,00 15,00 0 20,00
Theory class 24,00 56,00 0 80,00
Hands-on class 16,00 34,00 0 50,00
Total 45,00 105,00 0 150

Bibliography

  • Goodfellow, Ian (2016). Deep learning. Cambridge, Massachusetts: The MIT Press. Catàleg
  • Bishop, Christopher M. (2006). Pattern recognition and machine learning. New York: Springer. Catàleg
  • François Chollet (2018). Deep Learning with Python. Manning Publications.
  • Adrian Rosebrock (2017). Deep Learning for Computer Vision with Python. PyImageSearch.

Assessment and Grading

Assessment activities:

Description of the activity Assessment Activity % Remediable subject
Lab assignments These lab assignments are evaluated on the basis of the Python code delivered by the students and a report explaining what has been done, what problems have aroused, and how the students have solved these problems. 30 No
Student Presentations Students will be evaluated based on the clarity of the presentations and their ability to defend the work presented, including answering questions by their piers. 20 No
Exam Coherence of answers with respect to the reviewed contents. Synthesis ability. 50 Yes

Grading

About evaluation:

50% Exam.
30% Lab's evaluation (Every exercise Mark >= 4/10)
20% Student's presentation

Specific criteria for the "No show" grade:
Lab assignments are mandatory. Failure to deliver a lab assignment implies that the student will not be evaluated in the module.

Single Assessment:
Exam of theoretical and practical contents of the subject. In order to be able to do this, it will be necessary to first deliver two alternative labs that will be provided to students who opt for the single assessment.

The final grade will be 80% of the exam and 20% of the labs.

If deemed necessary, a meeting will be organized where teachers can ask questions they deem appropriate about the lab reports delivered.

For the students to be elegible for the single assessment, they should apply within the deadlines set and in accordance with the procedures and criteria established by the Governing Board of the center.

Minimum requirements to pass:
To pass the module, the global mark must be >= 5/10

Mentorship

Students can arrange tutorial sessions with the professor by contacting the professor via email. Whenever possible, questions and doubts will be solved via email. Otherwise the tutorial will be conducted using Zoom or face-to-face.

Communication and interaction with students

Presentation of information about the course and course activities will be done through Moodle. Google meet will be used for non-contact sessions. All message communication between the professors and the students will be made by internal Moodle messaging system or by email. Students will use Moodle to upload reports.

Remarks

Students must be familiar with programming in Python.

Escull quins tipus de galetes acceptes que el web de la Universitat de Girona pugui guardar en el teu navegador.

Les imprescindibles per facilitar la vostra connexió. No hi ha opció d'inhabilitar-les, atès que són les necessàries pel funcionament del lloc web.

Permeten recordar les vostres opcions (per exemple llengua o regió des de la qual accediu), per tal de proporcionar-vos serveis avançats.

Proporcionen informació estadística i permeten millorar els serveis. Utilitzem cookies de Google Analytics que podeu desactivar instal·lant-vos aquest plugin.

Per a oferir continguts publicitaris relacionats amb els interessos de l'usuari, bé directament, bé per mitjà de tercers (“adservers”). Cal activar-les si vols veure els vídeos de Youtube incrustats en el web de la Universitat de Girona.