10-601B Generalization and Overfitting: Sample Complexity Results for Supervised Classification
From Cohen Courses
Revision as of 21:46, 21 February 2016 by Tdick (talk | contribs) (Created page with "This a lecture used in the Syllabus for Machine Learning 10-601B in Spring 2016 === Slides === * [http://curtis.ml.cmu.edu/w/courses/images/c/c0/Sample-complexity1.pdf s...")
This a lecture used in the Syllabus for Machine Learning 10-601B in Spring 2016
Slides
Readings
- Mitchell Chapter 7
What you should remember
- Distributional Learning Formulation.
- Definition of sample complexity vs time complexity.
- How sample complexity grows with 1/epsilon, 1/delta, and |H|...
- in the noise free case.
- in the "agnostic" setting, where noise is present and the learner outputs the smallest error-rate hypothesis.