Objectives of the training
This intensive course enables participants to master Python in the context of developing Artificial Intelligence solutions.Targeted audience
Developers, engineers, data scientists, anyone wishing to retrain in AIPrerequisite
Basic programming knowledge (preferably Python). Notions of mathematics/statistics (linear algebra, probability).Trainers
Benefits for Participants
• Master the fundamentals of Python for AI.
• Manipulate and visualize data with Python libraries.
• Implement Machine Learning algorithms with Scikit‑learn.
• Create Deep Learning models with TensorFlow/Keras.
• Apply AI to concrete use cases: NLP, vision, prediction.
Course architecture
Day 1: Python fundamentals for Data Science
Chapter 1: Syntax and basic structures
• Variables, types, loops, functions
• Lists, dictionaries, tuples
Chapter 2: Object‑oriented programming
• Classes, inheritance, encapsulation
Chapter 3: Work environments
• Jupyter Notebook, VS Code, Google Colab
Workshop 1: Creation of a mini object‑oriented Python project
Day 2: Data manipulation and visualization
Chapter 4: NumPy and Pandas
• Multidimensional arrays
• Data cleaning and transformation
Chapter 5: Visualization with Matplotlib and Seaborn
• Statistical charts
• Correlations and distributions
Workshop 2: Exploratory analysis of a dataset (Titanic, Iris, etc.)
Day 3: Machine Learning with Scikit‑learn
Chapter 6: Supervised learning
• Linear and logistic regression
• Decision trees, Random Forest
Chapter 7: Unsupervised learning
• K‑means, PCA, hierarchical clustering
Chapter 8: Model evaluation
• Accuracy, precision, recall, F1‑score
Workshop 3: Implementation of a complete classification model
Day 4: Deep Learning with TensorFlow/Keras
Chapter 9: Artificial neural networks
• Perceptron, MLP, activation functions
Chapter 10: Training and validation
• Overfitting, early stopping, dropout
Chapter 11: Image processing
• CNNs, image recognition
Workshop 4: Creation of an image recognition model (MNIST)
Day 5: Advanced AI applications
Chapter 12: Natural language processing (NLP)
• Tokenization, TF‑IDF, Word Embeddings
• Text classification models
Chapter 13: Deploying AI models
• Saving with Pickle/Joblib
• Flask API for inference
Chapter 14: Final project
• Choice of a real‑world use case (NLP, vision, prediction)
• Presentation of results
Workshop 5: Deployment of an AI model via a Flask API
Pedagogical details
Type of training
Private or personalized training
Do you have several employees interested in the same training course? Whether in person at your offices or remotely in virtual mode, we offer private training courses tailored to your team's needs. Group rates are available. Contact us for more details or request a quote online.
Request a quotePrivate or personalized training
Do you have several employees interested in the same training course? Whether in person at your offices or remotely in virtual mode, we offer private training courses tailored to your team's needs. Group rates are available. Contact us for more details or request a quote online.
Request a quote