Intro to Deep Learning

Graduate Course, Duke University, ECE Department, 2019

Various topics covered in this course: Intro to Deep Learning

Lecture Topics

  1. Mathematical Background, Modeling and Validation Methods
  2. Computation Graphs and Large-Scale Logistic Regression
  3. Deep Feed-Forward Networks, Back-propagation
  4. Regularization for Deep Learning
  5. Optimization for Training Deep Networks, Stochastic Gradient Descent,
  6. Algorithms with Adaptive Learning Rates
  7. Convolutional Neural Networks (for image/text analysis)
  8. Graphical Models
  9. Deep Belief Networks
  10. Recursive Neural Networks, Long Short Term Memory
  11. Language Modeling
  12. Deep Learning in Practice
  13. Linear Factor Models
  14. Autoencoders
  15. Representation Learning
  16. Probabilistic Modeling for Deep Learning
  17. Monte Carlo Methods
  18. Approximate Inference
  19. Deep Generative Models
  20. Boltzmann Machines, and Restricted Boltzmann Machines
  21. Variational Auto-encoders
  22. Reinforcement Learning
  23. Generative Adversarial Networks