| 1 |
Lecture 0: Introduction |
Lecture 1: Smoothing and Additive 1 |
Lab 1: Intro to R |
|
Homework 0 |
|
|
| 2 |
Lecture 2: Smoothing and Additive 2 |
Lecture 3: Smoothing and Additive 3 |
Lab 2: Smoothing/GAM |
|
Homework 1 |
|
|
| 3 |
Lecture 4: Unsupervised learning/clustering 1 |
Lecture 5: Unsupervised learning/clustering 2 |
Lab 3: Unsupervised Learning 1 |
|
Homework 2 |
|
|
| 4 |
Lecture 6: Unsupervised learning/clustering 3 |
Lecture 7: Bayesian 1 |
Lab 4: Unsupervised Learning 2 |
|
|
|
|
| 5 |
No Class |
Lecture 8: Bayesian - Basic models, computation 2 |
Lab 5: Bayes/Stan |
|
Homework 3 |
|
|
| 6 |
Lecture 9: Bayesian - hierarchical models/LDA 3 |
Lecture 10: Scalability: concepts up/out |
Lab 6: Bayes/LDA |
A-Section 1: Relation with SVM and Logistic Regression |
|
|
Milestone 1: Group formation and signup |
| 7 |
Lecture 11: Nueral Net Basics & Math |
No Class |
Lab 7: Scalability xPUs, cloud |
|
Homework 4 |
Midterm |
|
| Spring Break |
|
|
|
|
|
|
|
| 8 |
Lecture 12: Deep Feed Forward 1 |
Lecture 13: Deep Feed Forward 2 |
Lab 8: Intro to Keras |
A-Section 2: Regularization/Dropout |
Homework 5 |
|
|
| 9 |
Lecture 14: Regularization |
Lecture 15: Optimization |
Lab 9: Regularization |
A-Section 3: Neural style transfer learning |
|
|
|
| 10 |
Lecture 16: CNN |
Lecture 17: RNN |
Lab 10: CNN |
A-Section 4: Examples of ConvNets: LeNet, AlexNet, VGG-15, ResNet and Inception |
Homework 6 |
|
Milestone 2: Lit review, pre-EDA and SOW |
| 11 |
Lecture 18: RNN |
Lecture 19: Autoencoders |
Lab 11: RNN |
A-Section 5: Deep Gans |
|
|
|
| 12 |
Lecture 20: Generative Models and GANS |
Lecture 21: Databases (SQL, NoSQL) |
|
|
|
|
Milestone 3: EDA, Baseline analysis |
| 13 |
Lecture 22: Guest Lecture - Aparna Kumar, Spotify |
Lecture 23: Adversarial Examples |
|
|
|
|
|
| 14 |
Reading Week |
|
|
|
|
|
Milestone 4: Final Project Due |