Difference between revisions of "10-601 Neural networks and Deep Belief Networks"
From Cohen Courses
Jump to navigationJump to search (→Slides) |
|||
| Line 11: | Line 11: | ||
=== What You Should Know Afterward === | === What You Should Know Afterward === | ||
| − | + | * What functions can be expressed with multi-layer networks that a single layer cannot express | |
| − | * What can be | + | * The backpropagation algorithm, and what loss is associated with it |
| − | * | + | * In outline, how deep neural networks are trained |
| − | * | ||
| − | |||
Revision as of 15:44, 23 September 2014
This a lecture used in the Syllabus for Machine Learning 10-601 in Fall 2014
Slides
- William's slides: in Powerpoint, in PDF
Readings
- Mitchell: Ch. 4, or Bishop: Ch. 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
