Vision par ordinateur

Catalog of Télécom SudParis courses

Code

IGFF IMA 4103

Level

M1

Graduate

Graduate

Semester

Spring

Domain

Image

Program

Programme Ingénieur

Language

Anglais/English

ECTS Credits

3

Class hours

30

Workload

75

Program Manager(s)

Department

  • Advanced Research and Techniques for Multidimensional Imaging Systems

Educational team

Organisation

Cours/TD/TP/projet/examen : 21 / 0 / 9 / 0 / 0

Learning objectives

This module aims to familiarize students with the main approaches models and explanatory theories in the field of artificial intelligence used to solve practical applications and problems. In the first part the focuse is put at presenting the fundamental notions in the field of neural networks convolutional neural networks with the purpose of automatically identify the relevant semantic content existing in multimedia documents.
- Aquire specific notions used in the field of deep learning such as: score functions and loss functions artificial neural networks convolutional neural networks classification/regression systems deep network architectures used in practical applications.
- Describes and determine the steps required to train a system that uses deep learning architectures.
- Highlights the relationships between different systems topologies used in deep learning frameworks.

CDIO Skills

  • 1.1.1 - Mathematics (including statistics)
  • 1.2 - Core engineering fundamental knowledge and other disciplines
  • 2.1.1 - Problem Identification and Formulation
  • 2.1.2 - Modeling
  • 2.4.3 - Creative Thinking

Prerequisites

Aucun

Content

- familiarize students with the main model approaches and explanatory theories in the field of artificial intelligence and 3D vision

Evaluation

continuous evaluation (CE) based on labs. Here the final grade is the average of grades for individual lab reports.

References

1. I. Goodfellow Y. Bengio A. Courville „Deep learning” MIT Press 2016. ISBN: 0262035618 http://www.deeplearningbook.org.
2. F. Chollet “Deep Learning with Python” Manning Publications Co. 2017 ISBN 9781617294433.
3. A. Rosebrock “Deep Learning for Computer Vision with Python” PyImageSearch 2017.
4. S. Haykin “Neural networks and learning machines” Person Press SBN: 978-0-13-147139-9