English speakers: Data Science for Research - CEDRE Program 3 - Analysis of research data: Introduction to Artificial Intelligence through Machine Learning - ST CHARLES

- Connect the concepts of Data Analysis, Artificial Intelligence (AI), and Machine Learning (ML).
- Identify types of learning (supervised, unsupervised, and reinforcement) and their associated algorithms.
- Introduction to the use of devoted Python libraries : the Scikit-Learn package.
- Identify and implement the steps of Machine Learning : 1) Data collection, 2) Cleaning and descriptive analysis, 3) Mixing and splitting, 4) Models and hyperparameters, 5) Model validation and performance measurement, 6) Model deployment.
- Lead a Machine Learning project in its entirety.
- Understansd advanced data analysis through different Artificial Intelligence techniques.

1. L'Intelligence Artificielle : les concepts.
2. Rappel de prétraitement de données et réduction de dimensionalité P2: sélection des caractéristiques.
3. Processus du ML : collecte de données, nettoyage et analyse de données, mélange et séparation de données, apprentissage, modèles et hyperparamètres, entraînement d'un modèle, validation, exploitation, optimisation d'un modèle.
4. Concepts de ML, algorithmes supervisés et non supervisés. Mesures de la qualité : accuracy, precision, recall, F1 score, R2, MSE. Sur-apprentissage et Sous-apprentissage.
5. Régression linéaire et algorithmes de la librairie Scikit Learn
6. Classification et algorithmes de la librairie Scikit Learn : k-NN pour classification, machine à vecteurs supports, classification Bayésienne naïve, régression logistique, etc.
7. Clustering et Scikit Learn: k means, hiérarchique.

- Solid understanding of programming in the Python language or completion of the Modules 1 and 2 of the CEDRE Program.
- Ordinateur, personnel ou professionnel.
- Installation préalable de Anaconda https://www.anaconda.com/..

At the end of this module, students will have acquired the skills to:
- Understand concepts related to AI.
- Differentiate between Machine Learning (ML) and Deep Learning.
- Use the technical vocabulary of ML.
- Know the method for developing their own ML algorithms.
- Explain and use different ML algorithms.
- Implement processes to solve business problems through ML.
Additionally, the student will have developed skills to:
- Collect and gather data and manipulate it using Python.
- Statistically analyze a data source with Python.
- Communicate simple observations through graphs and specialized modules.
- Identify variables in a data source.
- Transform variables for use in a mathematical model.
- Be able to sort data and explain decisions.
- Train ML models.
- Modify models (adjust hyperparameters) to improve performance.
- Measure model performance according to the type of problem.
- - Optimize models.

---

---

---