Deep Learning (DL) has attracted much interest in a wide range of applications such as image recognition, speech recognition and artificial intelligence, both from academia and industry. This lecture introduces the core elements of neural networks and deep learning, it comprises:

(multilayer) perceptron, backpropagation, fully connected neural networksloss functions and optimization strategiesconvolutional neural networks (CNNs)activation functionsregularization strategiescommon practices for training and evaluating neural networksvisualization of networks and resultscommon architectures, such as LeNet, Alexnet, VGG, GoogleNetrecurrent neural networks (RNN, TBPTT, LSTM, GRU)deep reinforcement learningunsupervised learning (autoencoder, RBM, DBM, VAE)generative adversarial networks (GANs)weakly supervised learningapplications of deep learning (segmentation, object detection, speech recognition, ...)