EE104: Introduction to Machine Learning

Stanford University, Spring Quarter 2018


  • Homework 5 is now available. It is due on Friday, June 1, by 5pm on Gradescope.

  • Slides from the optional ERM section have been posted.

  • Homework 4 is now available. It is due on Wednesday, May 23, by 5pm on Gradescope.

  • Homework 3's due date has been moved up to Wednesday, May 16. It's only two problems, so we're sure it will be managable.

  • We've posted a link to EmpiricalRiskMinimization.jl. You won't need it until Homework 5. Let us know what bugs you find.


Professor Sanjay Lall and Professor Stephen Boyd

Course description

Introduction to machine learning. Formulation of supervised and unsupervised learning problems. Regression and classification. Data standardization and feature engineering. Loss function selection and its effect on learning. Regularization and its role in controlling complexity. Validation and overfitting. Robustness to outliers. Simple numerical implementation. Experiments on data from a wide variety of engineering and other disciplines. In this initial offering, enrollment is limited to 50 students. Undergraduate students should enroll for 5 units, and graduate students should enroll for 3 units.

Prerequisites: EE 103; EE 178 or CS 109; CS106A or equivalent.


There are no required or optional textbooks. Complete notes will be available online.

A useful reference will be the EE103 course textbook, Introduction to Applied Linear Algebra – Vectors, Matrices, and Least Squares. The book is now complete.


  • Tuesdays and Thursdays, 9:00–10:20am in Hewlett 201

  • 19 lectures, the first lecture is on April 3, the last is on June 5.