Deep learning

Basics of deep learning
  1. Introduction, learning representations
  2. Empirical risk minimization, standard loss functions, linear classification, stochastic optimizers
  3. Hidden layers, deep feedforward networks, backpropagation, regularization ideas, normalization methods
  1. Convolutional networks (CNNs), classifying images
  2. ConvNet architectures, representations inside CNNs: visualizing networks/inceptionism, transfer learning, image retrieval with CNNs
  3. "Deep" computer vision beyond classification: Verification tasks, object detection architectures, semantic segmentation
  4. Deep image generation: generating CNNs, adversarial networks
  5. Autoencoders, variational autoencoders, image analogies
Language/sequence understanding
  1. Word embeddings, word2vec and other variants, convolutional networks for natural language
  2. Recurrent neural networks, deep learning on sequences, deep RNNs, LSTMs, GRUs, deep machine translation
  3. Sequence2sequence, architectures with attention and long-term memory
  1. Deep reinforcement learning