Deep Learning for Image Analysis

Deep learning has achieved formidable results in the image analysis field in recent years, in many cases exceeding human performance. This success opens paths for new applications, entrepreneurship and research, while making the field very competitive.

This course aims at providing the students with the theoretical and practical basis for understanding and using deep learning for image analysis applications.


Fall 2023 edition: IASD master

Courses will take place at:

PariSanté Campus

2-10 rue Rue d'Oradour-sur-Glane 

75015 PARIS

Schedules and classrooms are available here:

Winter 2022-2023 edition: IASD master

Courses will take place at:

PariSanté Campus (Classroom S 0.8)

2-10 rue Rue d'Oradour-sur-Glane 75015 PARIS

According to the following schedule:

Date Time
06/01 13h45
13/01 13h35
20/01 13h45
27/01 13h45
03/02 13h45
10/02 13h45
17/02 13h45
24/02 13h45

The course material is available here:

Fall 2022 edition: Mines Paris


Date Time Classroom
20/09 13h45 MDM-AB
27/09 13h35
04/10 13h45
11/10 13h45
19/10 13h45
25/10 13h45
02/11 13h45
8/11 13h45

Winter 2021-2022 edition: IASD master

The course will be held at Mines Paris: 60 Bd. Saint-Michel (Paris 6ème). Classrooms are given in the timetable below.

Each session (except the first) will begin with two hours of lectures, followed by one hour of practical work. The students must bring their laptops with a configured WiFi access to eduroam.

Lessons and notebooks can be downloaded from:

Note that the exam will be held at Dauphine university, amphithéâtre 9


Date Time Classroom
12/01 8h30-11h45 L-224
19/01 8h30-11h45 L-118
26/01 8h30-11h45 L-213
02/02 8h30-11h45 V-106A
09/02 8h30-11h45 1-L-118
16/02 8h30-11h45 L-316
23/02 8h30-11h45 V-106A
09/03 8h30-11h45 L-109
23/03 (exam) 10h00-11h30 Dauphine, Amphi 9

Internships and PhD thesis proposals at Mines Paris - CMM

Fall 2021 edition: MINES ParisTech (MP1523/5)


Date Time Classroom Teaching assistant
21/09 13h45 L-218 Tarek Zenati
28/09 13h35 L-213 Mateus Sangalli
05/10 13h45 L-118 Daniel Zyss
12/10 13h45 L-224 Valentin Penaud-Polge
20/10 9h00 L-109 Thomas Langrognet
26/10 13h45 L-109 Martin Bauw
02/11 13h45 L-109
9/11 13h45 L-218

Winter 2020 edition: IASD Master

Invited speakers

  • Vincent Morard (General Electric) : AI for medical images: an industrial point of view
  • Bruno Figliuzzi (CMM, Mines Paris) : Segmentation d'images de rhéologie par réseaux de neurones convolutionnels
  • Sébastien Lefèvre (IRISA) : Deep Learning in Remote Sensing: Challenges and Results
  • Claire-Hélène Demarty (InterDigital) : Deep Learning for post production in movie industry
  • Camille Breuil et Cédric Meurée (aiVision): L'aide au diagnostic chez aiVision: exemple de la rétinopathie diabétique
  • Diego Tuccillo (Instituto de Astrofisica de Canarias): Deep learning applications in Astronomy
  • Martin Bauw (CMM, Mines Paris): détection d'anomalies
  • Valentin Penaud-Polge (CMM, Mines Paris): couches paramétriques

Fall 2020 edition: MINES ParisTech (MP1523/5)

Travaux pratiques

Link to download practical sessions material:

The following assignments will be available from:

Winter 2019 edition: IASD Master

Teaching assistants

  • David Duque
  • Leonardo Gigli
  • Arthur Imbert
  • Tristan Lazard

Fall 2019 Edition: ATHENS MP10

Invited speakers

  • Marc Huertas (Canaries Astrophysics Institute; Observatoire de Paris)
  • Maximilian Jaritz (
  • Olivier Moindrot (Owkin)
  • Bogdan Stanciulescu (CAOR, MINES ParisTech)

Teaching assistants

  • Eric Bazan
  • David Duque
  • Leonardo Gigli
  • Arthur Imbert
  • Tristan Lazard

Fall 2018 Edition: ATHENS MP10

Invited speakers

  • Pierre Fillard (Therapixel)
  • Marc Huertas-Company (Canaries Astrophysics Institute; Observatoire de Paris)
  • Bogdan Stanciulescu (CAOR, MINES ParisTech)
  • Pauline Luc (Facebook AI Research)

Teaching assistants

  • Robin Alais
  • Joseph Boyd
  • Leonardo Gigli
  • Peter Naylor
  • Robin Alais
deep/start.txt · Last modified: 2023/09/19 15:59 by edecenciere
CC Attribution-Share Alike 4.0 International
Driven by DokuWiki Recent changes RSS feed Valid CSS Valid XHTML 1.0