Stat 588 Data Science II
Deep learning with an in-depth presentation of the algorithms and efficient coding. Tensors. Multi-layer perceptron. Backpropagation. Graphs of operators. Automatic differentiation. Convolutional and pooling layers. Initialization and optimization. Dropout and batch normalization. Autoencoders. Computer vision examples.
Prerequisite
Stat 587 or equivalent. Basic Python programming. Linear algebra at the upper-undergraduate level is recommended.