What This Document Is
This is the second homework assignment for Carnegie Mellon University’s Advanced Introduction to Machine Learning course (10-715), Fall 2015, due October 19, 2015. It focuses on the application of Expectation-Maximization (EM) algorithms, Mixture Models, Principal Component Analysis (PCA), and duality concepts.
Why This Document Matters
This assignment is intended for students enrolled in the 10-715 Machine Learning course. It serves as a practical exercise to reinforce theoretical concepts covered in lectures, specifically requiring students to implement algorithms in Octave. Successful completion demonstrates understanding of core machine learning techniques and programming proficiency.
Common Limitations or Challenges
This document is a problem set, not a learning resource. It assumes prior knowledge of the covered topics. It does not provide detailed explanations of the underlying machine learning concepts themselves. Students are expected to have learned these concepts in class.
What This Document Provides
The full document includes: detailed assignment guidelines, specific programming tasks (including function signatures for Octave code), a link to a code handout with function stubs, submission instructions for Autolab, and point values for each question. The first problem involves deriving and implementing an EM algorithm for a Mixture of Bernoullis model. It also outlines submission requirements regarding file format, size, and execution time.