CENTURI Training course
CENTURI Data Weeks - Part 2
Intro to Biological Data - March 3-7, 2025
Taught by Léo Guignard, Martin Lardy, Marc-Eric Perrin, Matthieu Gilson & Paul Villoutreix
This course is the second part of the Data Weeks course. Find part 1 HERE.
The courses will all take place in the Hexalab.
This training includes four different courses, extended over a week:
1. The Python course, taught by Léo Guignard ; Beginner Level on March 3 ; Advanced on March 4
2. The Machine Learning & Deep Learning Basis course, taught by Martin Lardy & Marc-Erin Perrin ; on March 5
3. The Deep Learning Advanced course, taught by Matthieu Gilson from INT ; on March 6 and March 7 morning
4. The Data Analysis course, taught by Paul Villoutreix ; on March 7 afternoon
Students attending Python and Deep Learning Begginer/Basis courses must follow-up with the Advanced courses.
Students who do not require the Begginer/Basis courses can attend directly the Advanced courses.
You can find courses details here bellow:
The Python course : (Monday March 3rd & Tuesday March 4th)
Getting Comfortable with Coding:
Environment Setup: Tips for creating an efficient coding environment.
Virtual Environments: Why they’re essential for managing dependencies.
Version Control (Git): Benefits of tracking code changes and collaborating.
Useful Tools: Overview of helpful coding tools.
Python Basics: Variables, Conditionals, and Loops: Introduction to Python's core building blocks.
Classes in Python: Why and When to Use Them: Understanding the importance of classes for organizing code.
Using Classes: How to implement classes effectively.
Organizing and Publishing Code:
Code Organization: Best practices for structuring code.
Local Installations: Making code “pip installable” locally.
Online Publishing: Steps to publish code as an installable package online.
The Machine Learning course & Deep Learning Basis course : (Wednesday March 5th)
Prerequisites: basic Python skills, computer with Internet access.
Machine Learning morning:
Supervised learning (getting to grips with sklearn, svm, random forest, etc.)
Unsupervised: dimension reduction and clustering (pca, umap etc. )
Deep learning for beginners:
Key concepts (definition of layers, neurons, optimization, back propagation, getting to grips with a neural network with tp on Kaggle)
Supervised: segmentation with unet
Getting to grips with the pytorch library
The Deep Learning Advanced course: (Thursday March 6th & Friday March 7th morning)
Prerequisites: pytorch (Deep learning débutant)
Advanced Deep Learning:
architectures of deep learning networks to extract information patterns
application to analysis of images and graphs
The Data Analysis course: (Friday March 7th afternoon)
Prerequisites : Basic Python skills, data handling (numpy, pandas), data visualisation
Dimensionality reduction - PCA, Matrix Factorisation, UMAP, t-SNE
Data integration: Multi-omics analysis, Joint Matrix Factorisation
High-dimensional data.
How to deal with dimension reduction, variety parametrisation and clustering?
Time permitting, more advanced tools such as topological data analysis will be covered.
Please fill the form below to apply.
For any additional information, please contact Mélina De Oliveira (melina.de-oliveira@univ-amu.fr).