Deep Learning

Obtained with a grade of 83/100, multiple subject have been treated:

• Introduction to Neural Networks (Perceptron, MLP...)
• Theory of the Gradient Descent (Learning Rate Decay...)
• Theory of ConvNets (convolution, pooling...)
• Case study (AlexNet, VGG, GoogLeNet, ResNet...)
• Visualization (Manifold Untangling, t-sne...)
• Advanced optimization (Momentum, NAG, AdaDelta, Adam...)
• Unsupervised Learning (GAN, Context Encoder...)
• RCNN and derivates