| 9/1 |
|
Lecture 1: What is Data Science? General introduction. |
Lecture 2: Data + RegEx |
|
R:HW0 |
| 9/7 |
No Lecture (Holiday) |
Lecture 3: Web Scraping + PANDAS |
Lecture 4: Advanced PANDAS |
|
R:HW1 - D:HW0 |
| 9/14 |
Lecture 5: kNN Regression and Linear Regression |
Lecture 6: Multi and Poly Regression |
Lecture 7: Modeling knn and Linear R with skleanr |
|
R:HW2 - D:HW1 |
| 9/21 |
Lecture 8: Basic Statistics for Data Science |
Lecture 9: Inference: Bootstrap and CI |
Lecture 10: Hypothesis Testing & Predictive CI |
Advanced Section 1: Linear Algebra and Hypothesis Testing |
R:HW3 - D:HW2 |
| 9/28 |
Lecture 11: Cross-Validation & Model Selection |
Lecture 12: Regularization: Ridge & Lasso |
Lecture 13: Estimation of regularization parameter; Hands on |
Advanced Section 2: Methods of regularization and their justifications |
Milestone 1 |
| 10/5 |
Lecture 14: Visualization for Communication |
Lecture 15: kNN classification and Logistic Regression I |
Lecture 16: Case Study 1 |
|
R: HW4 (Individual) - D: HW3 |
| 10/12 |
No Lecture (Holiday) |
Lecture 17: Logistic Regression II |
Lecture 18: Multi class Classification (introduce softmax) |
Advanced Section 3: Generalized Linear Models |
Milestone 2 |
| 10/19 |
Lecture 19: Dealing with missing data, imputation |
Lecture 20: PCA |
Lecture 21: PCA and missing with data; hands on |
Advanced Section 4: Mathematical Foundations of PCA |
R:HW5 - D:HW4 |
| 10/26 |
Lecture 22: Classification Trees |
Lecture 23: Regression Trees Bagging RF |
Lecture 24: Tuning hyperparameters |
|
R:HW6 - D:HW5 |
| 11/2 |
Lecture 25: Boosting Methods for Regression |
Lecture 26: Boosting Methods for Classification |
Lecture 27: Case Study 2 |
Advanced Section 5: Stacking and mixture of experts |
|
| 11/9 |
Lecture 28: Neural Networks 1-Perceptron and MLP |
Lecture 29: Neural Networks 2- Anatomy of NN, design choices |
Lecture 30: Neural Netoworks 3- Design Choices II & Gradient Descent |
|
R:HW7 (Individual) - D:HW6 |
| 11/16 |
Lecture 31: Neural Networks 4 -Back Propagation, SGD |
Lecture 32: Regularization methods - Weight decay, data augmentation and dropout |
Lecture 33: Full worked example of regression and classification FFNN |
Advanced Section 6: Deeper into Solvers |
Milestone 3 |
| 11/23 |
Lecture 34: EthiCS |
No lecture (Thanksgiving) |
No lecture (Thanksgiving) |
|
R:HW8 - D:HW7 |
| 11/30 |
Lecture 35: Interpreting Prediction Models |
Lecture 36: Wrap-Up |
|
|
D: HW8 |
| 12/7 |
|
|
|
Reading Period |
|
| 12/14 |
|
|
|
Finals Week |
|