Neural networks and Deep Learning

Teacher(s)

Lee John; Missal Marcus (coordinator);

Language

English

Prerequisites

The prerequisite(s) for this Teaching Unit (Unité d’enseignement – UE) for the programmes/courses that offer this Teaching Unit are specified at the end of this sheet.

Content

(1) Necessity of a theoretical approach in neurosciences. (2) History of neural networks. (3) Most important types of neural networks. (4) Deep learning.
At the end of this unit, the student should be able to justify mathematical modeling of the central nervous system. The student should be able to explain the general principles of neural networks and have the knowledge and skills to simulate the behavior of elementary neural networks.

Teaching methods

Lectures (physically, remotely or both/comodal dep. sanitary conditions) and critical paper readings.

Evaluation methods

Oral examination (switching to written or distancial depending on the class size and sanitary conditions) or written exam with open questions.
Weighting of the final score: 50% for Marcus Missal's part, 50% for John Lee's part.

Other information

It is compulsory to participate to practical work, excercises and directed work to validate this unit. unjustified absence will cause a penalty at the examination of this unit that could include annulation of the exam for the academic year under consideration (0/20). In case of repeated no-show, even if justified, the teacher can propose to the jury to oppose inscription to the exam for this unit in agreemen with article 72 of RGEE.

Online resources

https://moodleucl.uclouvain.be/course/view.php?id=9189

Teaching materials

• https://moodleucl.uclouvain.be/course/view.php?id=9189

Faculty or entity

> FASB