10-601 Logistic Regression

This a lecture used in the Syllabus for Machine Learning 10-601B in Spring 2016

Slides

• William's lecture: in Powerpointm in Powerpoint

Readings

• Optional:
  • Murphy 8.1-3, 8.6
  • William's notes on SGD sec 1-3
  • Charles Elkan's notes on SGD

What You Should Know Afterward

• How to implement logistic regression.
• How to determine the best parameters for logistic regression models
• Why regularization matters for logistic regression.
• How logistic regression and naive Bayes are similar and different.
• The difference between a discriminative and a generative classifier.
• What "overfitting" is, and why optimizing performance on a training set does not necessarily lead to good performance on a test set.