Launching into Machine Learning en Français (Coursera)

Offered by Google Cloud,
Launching into Machine Learning en Français (Coursera)

À partir de l'histoire du machine learning, nous examinons les raisons pour lesquelles les réseaux de neurones fonctionnent si bien de nos jours dans différents problèmes liés à la science des données. Nous évoquons ensuite la façon d'aborder un problème d'apprentissage supervisé et le moyen d'y répondre en utilisant la descente de gradient. Cela implique de créer des ensembles de données menant à une généralisation ; nous évoquons les méthodes pour y parvenir de façon reproductible en utilisant l'expérimentation.

Class Deals by MOOC List - Click here and see Coursera's Active Discounts, Deals, and Promo Codes.

Objectifs du cours :

  • Identifier les raisons pour lesquelles le deep learning est actuellement en vogue
  • Optimiser et évaluer les modèles à l'aide des fonctions de perte et des statistiques de performance
  • Réduire les problèmes courants qui surviennent dans le machine learning
  • Créer des formations, des évaluations et des ensembles de données tests répétables et évolutifs

Course 2 of 5 in the Machine Learning with TensorFlow on Google Cloud en Français Specialization.

Syllabus

WEEK 1
Présentation du cours
Dans ce cours, vous acquerrez des connaissances de base sur le machine learning pour comprendre la terminologie que nous employons tout au long de la spécialisation. Nos professionnels Google du machine learning vous montreront également des conseils pratiques et les pièges à éviter, et vous donneront les codes et les connaissances nécessaires pour démarrer vos propres modèles de machine learning.

WEEK 2
Améliorer la qualité des données et l'analyse exploratoire des données
Dans ce module, nous allons présenter les problèmes liés à la qualité des données et les méthodes pour l'améliorer. Nous évoquerons ensuite les analyses exploratoires des données.

WEEK 3
Machine learning en pratique
Dans ce module, nous allons présenter certains des principaux types de machine learning. Nous passerons également en revue l'histoire du ML, ainsi que les événements l'ayant mené à ce système de pointe qui vous permet de développer rapidement vos connaissances en tant qu'utilisateur du ML.

WEEK 4
Optimisation
Dans ce module, nous vous expliquerons comment optimiser vos modèles de machine learning.

WEEK 5
Généralisation et échantillonnage
À présent, il est temps de répondre à une question plutôt étrange : dans quelle situation le modèle de ML le plus précis n'est-il pas le meilleur choix ? Comme indiqué dans le dernier module sur l'optimisation, la raison repose simplement sur le fait suivant : si un modèle dispose d'une métrique de perte de 0 pour l'ensemble de données d'entraînement, cela ne signifie pas qu'il fonctionnera correctement sur de nouvelles données dans le monde réel. Vous apprendrez à créer des ensembles de données d'entraînement, d'évaluation et de test reproductibles et à établir des références en matière de performances.

WEEK 6
Récapitulatif

Go to Class
MOOC List is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Related Courses

Exploratory Data Analysis (Coursera) Coursera
Johns Hopkins University

Exploratory Data Analysis (Coursera)

This course covers the essential exploratory techniques for summarizing data. These techniques are typically applied before formal modeling commences and can help inform the development of more complex statistical models. Exploratory techniques are also important for eliminating or sharpening potential hypotheses about the world that can be addressed by the data.

Jun 29th 2026
4 Weeks
Building R Packages (Coursera) Coursera
Johns Hopkins University

Building R Packages (Coursera)

Writing good code for data science is only part of the job. In order to maximizing the usefulness and reusability of data science software, code must be organized and distributed in a manner that adheres to community-based standards and provides a good user experience. This course covers the primary means by which R software is organized and distributed to others.

Jun 29th 2026
4 Weeks
Machine Learning: Clustering & Retrieval (Coursera) Coursera
University of Washington

Machine Learning: Clustering & Retrieval (Coursera)

Case Studies: Finding Similar Documents. A reader is interested in a specific news article and you want to find similar articles to recommend. What is the right notion of similarity? Moreover, what if there are millions of other documents? Each time you want to a retrieve a new document, do you need to search through all other documents? How do you group similar documents together? How do you discover new, emerging topics that the documents cover?

Jun 29th 2026
5-12 Weeks
Matrix Factorization and Advanced Techniques (Coursera) Coursera
University of Minnesota

Matrix Factorization and Advanced Techniques (Coursera)

In this course you will learn a variety of matrix factorization and hybrid machine learning techniques for recommender systems. Starting with basic matrix factorization, you will understand both the intuition and the practical details of building recommender systems based on reducing the dimensionality of the user-product preference space. Then you will learn about techniques that combine the strengths of different algorithms into powerful hybrid recommenders.

Jun 29th 2026
5-12 Weeks
Process Mining: Data science in Action (Coursera) Coursera
Eindhoven University of Technology

Process Mining: Data science in Action (Coursera)

Process mining is the missing link between model-based process analysis and data-oriented analysis techniques. Through concrete data sets and easy to use software the course provides data science knowledge that can be applied directly to analyze and improve processes in a variety of domains. Data science is the profession of the future, because organizations that are unable to use (big) data in a smart way will not survive. It is not sufficient to focus on data storage and data analysis. The data scientist also needs to relate data to process analysis.

Jun 29th 2026
5-12 Weeks
Machine Learning for Data Analysis (Coursera) Coursera
Wesleyan University

Machine Learning for Data Analysis (Coursera)

Are you interested in predicting future outcomes using your data? This course helps you do just that! Machine learning is the process of developing, testing, and applying predictive algorithms to achieve this goal. Make sure to familiarize yourself with course 3 of this specialization before diving into these machine learning concepts. Building on Course 3, which introduces students to integral supervised machine learning concepts, this course will provide an overview of many additional concepts, techniques, and algorithms in machine learning, from basic classification to decision trees and clustering.

Jun 29th 2026
4 Weeks
Reproducible Research (Coursera) Coursera
Johns Hopkins University

Reproducible Research (Coursera)

This course focuses on the concepts and tools behind reporting modern data analyses in a reproducible manner. Reproducible research is the idea that data analyses, and more generally, scientific claims, are published with their data and software code so that others may verify the findings and build upon them. The need for reproducibility is increasing dramatically as data analyses become more complex, involving larger datasets and more sophisticated computations.

Jun 29th 2026
4 Weeks
Data Science in Real Life (Coursera) Coursera
Johns Hopkins University

Data Science in Real Life (Coursera)

Have you ever had the perfect data science experience? The data pull went perfectly. There were no merging errors or missing data. Hypotheses were clearly defined prior to analyses. Randomization was performed for the treatment of interest. The analytic plan was outlined prior to analysis and followed exactly. The conclusions were clear and actionable decisions were obvious. Has that every happened to you? Of course not. Data analysis in real life is messy. How does one manage a team facing real data analyses? In this one-week course, we contrast the ideal with what happens in real life. By contrasting the ideal, you will learn key concepts that will help you manage real life analyses.

Jun 29th 2026
1 Week
Python Project for Data Science (Coursera) Coursera
IBM

Python Project for Data Science (Coursera)

This mini-course is intended to for you to demonstrate foundational Python skills for working with data. The completion of this course involves working on a hands-on project where you will develop a simple dashboard using Python. This course is part of the IBM Data Science Professional Certificate and the IBM Data Analytics Professional Certificate.

Jul 2nd 2026
1 Week
Statistical Inference (Coursera) Coursera
Johns Hopkins University

Statistical Inference (Coursera)

Statistical inference is the process of drawing conclusions about populations or scientific truths from data. There are many modes of performing inference including statistical modeling, data oriented strategies and explicit use of designs and randomization in analyses. Furthermore, there are broad theories (frequentists, Bayesian, likelihood, design based, …) and numerous complexities (missing data, observed and unobserved confounding, biases) for performing inference.

Jun 29th 2026
4 Weeks
Data Science Companion (Coursera) Coursera
MathWorks

Data Science Companion (Coursera)

The Data Science Companion provides an introduction to data science. You will gain a quick background in data science and core machine learning concepts, such as regression and classification. You’ll be introduced to the practical knowledge of data processing and visualization using low-code solutions, as well as an overview of the ways to integrate multiple tools effectively to solve data science problems.

Jul 3rd 2026
4 Weeks
Deep Learning for Business (Coursera) Coursera
Yonsei University

Deep Learning for Business (Coursera)

Your smartphone, smartwatch, and automobile (if it is a newer model) have AI (Artificial Intelligence) inside serving you every day. In the near future, more advanced “self-learning” capable DL (Deep Learning) and ML (Machine Learning) technology will be used in almost every aspect of your business and industry. So now is the right time to learn what DL and ML is and how to use it in advantage of your company. This course has three parts, where the first part focuses on DL and ML technology based future business strategy including details on new state-of-the-art products/services and open source DL software, which are the future enablers.

Jun 29th 2026
5-12 Weeks