Machine Learning
Develop intelligent software to automate routine labor, understand speech or images, make diagnoses in medicine and support basic scientific research ;
Solving the tasks that are easy for people to perform but hard for people to describe formally ;
Apply deep learning models for retrieval of information and machine translation ;
Develop an artificial Intelligence system for the deep neural network-based applications ;
Evaluation of various algorithms using deep learning ;
Design of intelligent model using algorithms of deep learning.
Introduction to DL
Perceptron and MLP,
Forward and Back Propagation gradient descent
Overfitting, Regularization and Gradient Checking
Optimization Algorithms (Mini-Batch, Adam, Learning Rate Decay…)
Hyperparameter Tuning and Batch Normalization
Foundations of CNN (Edge Detection, Padding, Strided, convolution, )
Deep Convolutions Architectures (Classical, ResNet, MobileNet, EfficientNet…)
Building Recurrent Neural Network
Long Short-Term Memory Neural Network
Gate Recurrent Unit Neural Network
Transfert de couche
Transfert de l’apprentissage
Apprentissage multitâche
Auto-encoders and unsupervised learning
Stacked auto-encoders and semi-supervised learning
Generative Adversarial Networks (GANs)
Consultez les ressources disponibles concernant ce module sur le moteur de recherche de la bibliothèque, ou accédez directement au cours de vos enseignants via la plateforme de téléenseignement de l’école « e-learn ».