Formation/Cours

• Se familiariser avec le langage de programmation Python et ses bibliothèques externes


• Comprendre et appliquer les approches d’apprentissage supervisé et non supervisé


• Résoudre des problèmes concrets à l’aide de diverses techniques et algorithmes de machine Learning Découvrir les réseaux de neurones et l’apprentissage par renforcement


• Appliquer les normes industrielles et les bonnes pratiques en matière de déploiement de modèles

Contenu :

• Introduction to Machine Learning : Definition, Life Cycle, and state of the art in Machine Learning


• Python Crash : Refresh students’ memory of commonly useful Python syntax and methods.


• Python Crash : Work with external python libraries such as NumPy, Pandas and Matplotlib.


• Supervised Learning : Introduction to supervised models with the help of scikit – learn ; Understand different types of problems (classification and prediction ) ; Solve real -world problems using regression models, decision trees , and NLP ; Feature engineering, data collection , and states ; Learn about common pitfalls (overfitting, training/testing, parameter optimization). Production mode tips, APIs , and deployment ; Hands -on projects using realworld datasets.


• Unsupervised Learning : Introduction to unsupervised models ; Understanding clustering problems. Working with recommender systems for multiple use cases. Hands -on projects.


• Advanced Learning : Introduction to Reinforcement Learning ; Introduction to Neural Networks and their variants .