Master ML models, deep learning, and implementation with Scikit-learn, TensorFlow, and PyTorch
This training combines theory, demonstrations, and hands-on workshops to enable participants to design, train, and evaluate intelligent models using professional tools.
Is it for you ?
Python developers wishing to specialize in AI, software engineers or data engineers, technical project managers in innovation or R&D
Prerequisites
Good foundation in Python programming, general knowledge of mathematics (statistics, linear algebra), initial experience in data manipulation is a plus.
What You'll Walk Away With
- ✓ Understand the main Machine Learning and Deep Learning algorithms.
- ✓ Master the steps involved in data preparation for AI.
- ✓ Implement supervised and unsupervised learning models.
- ✓ Use Python libraries for AI development (Scikit-learn, TensorFlow, etc.).
- ✓ Evaluate and optimize model performance.
Training content
1 Introduction to AI algorithms
- Supervised vs. unsupervised learning
- Concepts of classification, regression, clustering
2 Data preparation
- Cleaning, encoding, normalization
- Train/test split, handling imbalanced data
3 Classic algorithms
- Linear and logistic regression
- Decision trees, Random Forest
- KNN, SVM
4 Practical workshop 1:
Implementation of a classification model with Scikit-learn
Objective: train a model on a real dataset (Iris, Titanic…)
5 Introduction to Deep Learning
- Artificial neural networks
- Activation function, backpropagation
6 Frameworks and tools
- TensorFlow vs PyTorch
- Using Jupyter Notebook and Google Colab
7 Advanced modeling
- Multilayer perceptrons (MLP)
- Convolutional neural networks (CNN) for images
- Recurrent neural networks (RNN) for time series
8 Evaluation and optimization
- ROC curves, confusion matrices
- Cross-validation, hyperparameter tuning
9 Practical workshop 2:
- Creation of a neural network with TensorFlow/Keras
- Objective: train an image recognition model (MNIST or CIFAR-10)
📌 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.