Master AI techniques from data preparation to model deployment
This five-day course enables participants to discover and deepen their use of Artificial Intelligence in Data Science. It combines theory and practice to learn how to design, train, and deploy AI models adapted to business needs through hands-on workshops.
Is it for you ?
Data scientists, data analysts, developers wishing to specialize in AI, software engineers, technical architects, and data-oriented technical project managers.
Prerequisites
Basic knowledge of Python, concepts in statistics and linear algebra, as well as familiarity with data science concepts.
What You'll Walk Away With
- ✓ Analyze and manipulate data using Python and core libraries such as NumPy, Pandas, and Matplotlib
- ✓ Prepare high-quality datasets through cleaning, normalization, and feature engineering
- ✓ Build supervised and unsupervised machine learning models using Scikit-learn
- ✓ Design and train neural networks with TensorFlow or PyTorch for practical use cases
- ✓ Deploy AI models via APIs and evaluate their performance in real-world environments
Training content
1 Fundamental concepts
- Definition of AI, Machine Learning, Deep Learning.
- Applications in Data Science.
2 Ecosystem and tools
- Python for AI.
- Key libraries: NumPy, Pandas, Matplotlib.
- Practical workshop:
- Exploration and visualization of a dataset.
3 Data collection and cleaning
- Handling missing data.
- Normalization and encoding.
4 Feature Engineering
- Variable selection and transformation.
- Practical workshop:
- Preparing a dataset for a predictive model.
5 Supervised learning
- Linear and logistic regression.
- Decision trees and Random Forest.
6 Unsupervised learning
- Clustering (K‑means).
- Dimensionality reduction (PCA).
- Practical workshop:
- Implementation of an ML model with Scikit‑learn.
7 Foundations of Deep Learning
- Neural network architecture.
- Activation functions and backpropagation.
8 Advanced frameworks
- TensorFlow vs PyTorch.
- Creation of a simple network.
- Practical workshop:
- Development of an image classification model.
9 Evaluation and optimization
- Performance metrics.
- Hyperparameters and tuning.
10 Deploying an AI project
- Integration into a real‑world environment.
- Deployment tools (Flask, FastAPI).
- Practical workshop:
- Deployment of an AI model via an API.
📌 Practical information
Our training sessions are offered in Montreal or Quebec City, in person or in a virtual classroom. Dates and locations are specified when you select your session below. If you have any questions, check out our FAQ.