Statistics for data science, machine learning with scikit-learn, model evaluation, an introduction to deep learning, then LLMs, AI APIs, RAG applications and agents.
Who it is for : Engineers, data profiles, developers, advanced students.
Courses in this field are being prepared: no session is scheduled yet. You can ask to be notified for each of them.
12 course(s) shown
Probability, inference, tests and regression: the statistical foundations of machine learning.
Supervised and unsupervised learning, overfitting, evaluation: the key concepts.
Build and evaluate machine learning models with Python.
Pipelines, models, cross-validation and hyperparameter tuning with scikit-learn.
Create and select relevant variables to improve your models.
Deal with missing values, outliers and inconsistent formats before modeling.
Metrics, validation, bias and interpretation of a model's results.
Neural networks, training and applications, with practical examples.
How large language models work and how to integrate them into applications.
Call AI APIs from your applications: requests, costs, errors and security.
Build applications that answer from your documents: chunking, retrieval and generation.
Design AI-based agents and automation workflows: tools, control and limits.
No course matches these filters. Change your search or reset the filters.
Describe your need: we will point you to the right course or build a program adapted to your team.