Computer vision and deep learning - Part 1

Catalog of Télécom SudParis courses

Code

IGSF IMA 4201

Level

M1

Graduate

Graduate

Semester

Fall

Domain

Image

Program

Programme Ingénieur

Language

Anglais/English

ECTS Credits

2,5

Class hours

25

Workload

50

Program Manager(s)

Department

  • Advanced Research and Techniques for Multidimensional Imaging Systems

Educational team

Organisation

Cours/TD/TP/projet/examen : 9/3/9/4

Learning objectives

At the end of this module, the student will be able to:
- master the principles and the main architectures of deep neural networks used in image processing/analysis
-take in hand and deploy the main development tools and software libraries of artificial intelligence solutions available today (Tensorflow, PyTorch ...)
- appropriate and experiment some existing artificial intelligence solutions

CDIO Skills

  • 1.3 - Advanced engineering fundamental knowledge, methods and tools
  • 2.1.2 - Modeling
  • 2.2 - Experimentation, investigation and knowledge discovery
  • 2.4.3 - Creative Thinking
  • 3.1.2 - Team Operation

Prerequisites

Aucun

Content

The objective is to discover the fundamental methods and techniques of artificial intelligence and in particular deep learning, in the context of computer vision. After an introduction setting out the fundamental theoretical principles, the different types of networks will be discovered. Withinthis context, the student will be required to install and configure popular neural network deployment platforms (Tensorflow, Pytorch...), then experiment and evaluate basic approaches.

Evaluation

Final note = Oral presentation of a topic proposed by the teaching team

Assessment formula

Note finale = Présentation orale d'un sujet proposé par l'équipe enseignante

References

- Polycopiés et bibliographie spécifiques remis par les intervenants
- Ian Goodfellow, Yoshua Bengio, Aaron Courville, “Deep Learning”, MIT Press.
-Les MOOC machine learning et deep learning