2022-2023 / INFO8010-1

Deep learning

Duration

25h Th, 10h Pr, 55h Proj.

Number of credits

 Master of Science (MSc) in Biomedical Engineering5 crédits 
 Master of Science (MSc) in Data Science5 crédits 
 Master of Science (MSc) in Electrical Engineering5 crédits 
 Master of Science (MSc) in Computer Science and Engineering5 crédits 
 Master of Science (MSc) in Computer Science and Engineering (double degree programme with HEC)5 crédits 
 Master of Science (MSc) in Data Science and Engineering5 crédits 
 Master of Science (MSc) in Computer Science5 crédits 
 Master of Science (MSc) in Computer Science (joint-degree programme with HEC)5 crédits 
 Master of Science (MSc) in Engineering Physics5 crédits 

Lecturer

Gilles Louppe

Language(s) of instruction

English language

Organisation and examination

Teaching in the second semester

Schedule

Schedule online

Units courses prerequisite and corequisite

Prerequisite or corequisite units are presented within each program

Learning unit contents

Latest developments in deep learning have enabled great and unprecedented advances in systems for visual recognition, speech and text understanding, or autonomous intelligent agents. In this context, this course is a deep dive into the details of deep learning architectures, focusing on learning end-to-end models for these tasks. Students will learn to implement, train and debug their own neural networks and gain a detailed understanding of cutting-edge research in the field. The course will also tour recent innovations in inference methods.

Topics to be covered (tentative and subject to change):

  • Fundamentals of machine learning
  • Multi-layer perceptron
  • Automatic differentiation
  • Training neural networks
  • Convolutional neural networks 
  • Computer vision
  • Recurrent neural networks
  • Attention and transformers
  • Auto-encoders and variational auto-encoders
  • Generative adversarial networks
  • Uncertainty

Learning outcomes of the learning unit

At the end of the course, the student will have acquired a solid and detailed understanding of the field of deep learning. He/she will have studied both well-established and novel algorithms (in theory and practice) and will also have become familiar with some of the many open research questions and challenges of the field.

This course contributes to the learning outcomes I.1, I.2, I.3, II.1, II.2, III.1, III.2, III.3, III.4, IV.1, IV.3, IV.4, V.2, VI.1, VI.2, VII.1, VII.2, VII.4, VII.5 of the MSc in data science and engineering.


This course contributes to the learning outcomes I.1, I.2, II.1, II.2, III.1, III.2, III.3, III.4, IV.1, IV.8, V.2, VI.1, VI.2, VII.1, VII.2, VII.4, VII.5 of the MSc in electrical engineering.


This course contributes to the learning outcomes I.1, I.2, II.1, II.2, III.1, III.2, III.3, III.4, IV.1, V.2, VI.1, VI.2, VII.1, VII.2, VII.4, VII.5 of the MSc in computer science and engineering.

Prerequisite knowledge and skills

Programming experience. Probability and statistics.

Following "ELEN0062 Introduction to Machine learning" before taking this class is strongly recommended.

Planned learning activities and teaching methods

  • Theoretical lectures
  • Homeworks
  • Programming project

Mode of delivery (face to face, distance learning, hybrid learning)

Lectures will taught face-to-face. Projects will be carried out remotely.

Recommended or required readings

Slides will be made publicly available on GitHub during the semester.

Exam(s) in session

Any session

- In-person

oral exam

Written work / report


Additional information:

The evaluation is divided into the following units:

  • Exam (50%)
  • Homeworks (10%)
  • Programming project (40%)
The programming project is mandatory to access the exam. 

Work placement(s)

Organizational remarks

The website for the course is https://github.com/glouppe/info8010-deep-learning 

Contacts

  • Teacher: Prof. Gilles Louppe (g.louppe@uliege.be)

Association of one or more MOOCs