|Home CV Publications Presentations Teaching Contact Software & Data HyperClas Hobbies Motto|
16) EPU Intelligence Artificielle : applications à la physique médicale (pdf).
15) LuxCarta Deep Learning Workshop Research and Industrial Application (Berges de Lac, Tunis), 11-12 Juin 2019.
LuxCarta, a leading provider of geospatial products, is pleased to offer a Research and Application Workshop aimed at training in Deep Learning for Computer Vision Applications, with a special focus on geospatial use cases. The workshop targets engineers and graduate students.
You will learn: Fundamentals of machine learning and deep learning concepts. Design of deep neural networks for computer vision applications. Implementation of deep learning architectures using Tensorflow for common vision applications, such as image classification and segmentation. Train and deploy your models to solve real-world problems.
Prerequisites: Technical background and programming skills. Basic understanding of machine learning concepts is an advantage.
Registration: Deadline for registration is May 17, 2019. Registration fee: 50 TND for students, 100 TND for salaried employees. For registration, a CV of the participant candidate must be sent to email@example.com. Space is limited. Register today.
14) Graphical models and learning course (MVA, ENS Paris-Saclay and Centrale Supelec, France), 2017 - present.
Lecture 3: Max flow, min cut. (pptx)
Lecture 6: Standard learning. (pdf)
Lecture 7: Modern learning. (pdf)
Lecture 8: Recommender systems. (pdf)
Lecture 9: Final remarks. (pdf)
13) Tutorial on Machine learning in remote sensing: best practice and recent developments (IGARSS conference, TX, USA), 2017. (slides)
12) Discrete optimisation course (Centrale Supelec, France), 12h of course + 6h of practical sessions, 2017 - present.
11) Mathematical methods course (Master Data Science & BA, Centrale Supelec, France), 25h, 2016 - present.
Lecture 1: Introduction. (pdf1)
Lecture 9: Partial Differential Equations. (pdf9)
Lecture 10: Complex Numbers and Variables. (pdf10)
Lecture 11: Shape of Data. (pdf11)
Homework 1. (pdf-homework1)
Homework 2. (pdf-homework2)
10) Spaceborne sensors and their applications course (Master PPMD, ENSG, France), 3h, 2013 (pdf).
9) Digital Imaging course (Master ISAB, University of Nice, France), 2h of course + 2h of practical sessions, 2012 - present.
8) Practical Sessions on Matlab (Master ISAB, University of Nice, France), 10h, 2012 - present.
7) Computer Vision course (TNTU, Ukraine), 8h, 2012.
6) Methods for Statistical Data Analysis (SI3, 1st year, University of Nice Sophia Antipolis, France), 39h, 2012.
5) Image Processing course (Traitement d'Images, ASI, 2ème année, Grenoble INP - ENSI3, France), 12h, 2010.
4) Matlab for Image Processing (continuing education) (Grenoble INP, France), 7 hours x 3 = 21 hours, December 2009 - January 2010.
3) Pattern Recognition course (University of Iceland, Iceland), September - November 2009.
Lecture 1: Introduction. (pdf)
Lecture 2: Mathematical Preliminaries. (pdf)
Lecture 3: Bayesian Decision Theory. (pdf)
Lecture 4: Maximum Likelihood Estimation. (pdf)
Lecture 5: Non-Parametric Classification. (pdf)
Lecture 6: Linear Discriminant Functions. (pdf)
Lecture 7: Feature Extraction for Representation and Classification. (pdf)
Lecture 8: Unsupervised Analysis. (pdf)
2) E-learning course of Mathematical Morphology (in the frame of Hyper-I-Net project), 2h, July 2009:
Part 5: Practical session on mathematical morphology. (pdf)
1) Practical Sessions on Image Processing (Traitement d'Images, SICOM, 2ème année, Grenoble INP - PHELMA, France), 48h, 2008 - 2010.
|Page updated on 24/07/2017|