10-601B Neural networks and Backprop
From Cohen Courses
Jump to navigationJump to searchThis a lecture used in the Syllabus for Machine Learning 10-601B in Spring 2016
Slides
Readings
- Mitchell: Ch. 4, Murphy Ch 16.5
What You Should Know Afterward
- What functions can be expressed with multi-layer networks that a single layer cannot express
- The backpropagation algorithm, and what loss is associated with it
- In outline, how deep neural networks are trained
