STAT 157, Spring 19

Table Of Contents

Units

• Introduction to Deep Learning
• Probability and Statistics
• Gradients, Chain Rule, Automatic Differentiation
• Linear Regression, Basic Optimization
• Likelihood, Loss Functions, Logisitic Regression, Information Theory
• Multilayer Perceptron
• Model Selection, Weight Decay, Dropout
• Numerical Stability, Hardware
• Machine Learning Problems and Statistical Environment
• Layers, Parameters, GPUs
• Convolutional Networks
• Basic Convolutional Networks
• Residual Networks and Advanced Architectures
• Computation Performance, Multi-GPU and Multi-Machine Training
• Image Augmentation, Fine Turning, Neural Style
• Object Detection
• Sequence Models and Language
• Recurrent Neural Networks
• Advanced Sequence Models
• Word2vec, FastText, GloVe, Sentiment Analysis
• Encoder-Decoder, Seq2seq, Machine Translation
• Attention, Transformer, BERT
• Convex Optimization, Convergence Rate
• Momentum, AdaGrad, RMSProp, Adam

Previous

20. Measuring Amazon Product Reviews Helpfulness

Next

Introduction to Deep Learning