Skip to content
Regression: Predicting House Prices
[+]
Expand All[+]
- Intro
- Regression Intro, gradient descent
- Regression cont.
- Assessing performance, error types + bias/variance tradeoff
- Overfitting, regularized regression, ridge regression
- Lasso regression, cross validation
Lectures:
- Section 2. Thurs, April 5 : Assignment 1 tips, Bias variance tradeoff.
You can view the notebooks by viewing the HTML version here. To try out the demo yourself, download the ipynb and data files and upload them to your JupyterHub
[Accessing SFrames (html | ipynb)]
[Bias-Variance demo (html | ipynb)]
[Philadelphia_Crime_Rate data]
Optional Readings:
Classification: Analyzing Sentiment
[+]
Expand All[+]
- Class intro
- Logistic regression, overfitting
- Decision trees
- Overfitting in decision trees, boosting
- Boosting cont., precision and recall
Lectures:
- Section 4. Thurs, April 19: MLE and dealing with categorial features
[Slides]
Optional Readings:
- Section 5. Thurs, April 26 : Tree ensembles.
[Slides]
Optional Readings:
Clustering and Similarity: Retrieving Documents
[+]
Expand All[+]
- Retrieving intro, kNN
- kNN methods for classification and regression
- Clustering and unsupervised learning intro, k-means
- Hierarchical clustering
Lectures:
- Section 6. Thurs, May 3: Missing data.
[Slides]
Optional Readings:
Recommending Products
[+]
Expand All[+]
- Recommender systems, performance metrics
Lectures:
- Section 8. Thurs, May 17: Matrices, PCA, and coordinate descent.
[groupby (html | ipynb)]
Deep Learning: Searching for Images
[+]
Expand All[+]
- Deep learning intro, single and multilayer networks
- Guest lecture
- Convnets, transfer learning, course wrapup
Lectures:
- Lecture 19. Tues, May 29:Guest Lecture: Carlos Guestrin (Apple, University of Washington)
- Section 10. Thurs, May 31: Marathon office hours