Deep Learning

Machine Learning

1. Develop intelligent software to automate routine labor, understand speech or images, make diagnoses in medicine and support basic scientific research ;

2. Solving the tasks that are easy for people to perform but hard for people to describe formally ;

3. Apply deep learning models for retrieval of information and machine translation ;

4. Develop an artificial Intelligence system for the deep neural network-based applications ;

5. Evaluation of various algorithms using deep learning ;

6. Design of intelligent model using algorithms of deep learning.

1. Foundations for DL

1. Introduction to DL

2. Perceptron and MLP,

3. Forward and Back Propagation gradient descent

2. Optimizing Deep Neural Networks

1. 1. Overfitting, Regularization and Gradient Checking

   2. Optimization Algorithms (Mini-Batch, Adam, Learning Rate Decay…)

   3. Hyperparameter Tuning and Batch Normalization

3. Convolution Neural Networks

   1. Foundations of CNN (Edge Detection, Padding, Strided, convolution, )

   2. Deep Convolutions Architectures (Classical, ResNet, MobileNet, EfficientNet…)

4. Recurrent Neural Networks

   1. Building Recurrent Neural Network

   2. Long Short-Term Memory Neural Network

   3. Gate Recurrent Unit Neural Network

5. Transfert Learning

1. 1. Transfert de couche

   2. Transfert de l’apprentissage

   3. Apprentissage multitâche

6. Dimensionality Reduction with Deep Learning

1. 1. Auto-encoders and unsupervised learning

   2. Stacked auto-encoders and semi-supervised learning

   3. 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 ».