Votre enseignant(e) vous guidera étape par étape, grâce à une vidéo en écran partagé sur votre espace de travail :

1. • 

   Understand the theory and intuition behind Deep Neural Networks, Residual Nets, and Convolutional Neural Networks (CNNs)

2. • 

   Apply Python libraries to import, pre-process and visualize images

3. • 

   Perform data augmentation to improve model generalization capability

4. • 

   Build a deep learning model based on Convolutional Neural Network and Residual blocks using Keras with Tensorflow 2.0 as a backend

5. • 

   Compile and fit Deep Learning model to training data

6. • 

   Assess the performance of trained CNN and ensure its generalization using various KPIs such as accuracy, precision and recall

7. • 

   Understand the theory and intuition behind GradCam and Explainable AI

8. • 

   Visualize the Activation Maps used by CNN to make predictions using Grad-CAM