Difference between revisions of "10-601 Neural networks and Deep Belief Networks"
From Cohen Courses
Jump to navigationJump to search (Created page with "This a lecture used in the Syllabus for Machine Learning 10-601 in Fall 2014 === Slides === * TBD === Readings === * Mitchell: Ch. 4, or Bishop: Ch. 5 === What You Sh...") |
|||
| (4 intermediate revisions by 2 users not shown) | |||
| Line 1: | Line 1: | ||
| − | This a lecture used in the [[Syllabus for Machine Learning 10- | + | This a lecture used in the [[Syllabus for Machine Learning 10-601B in Spring 2016]] |
=== Slides === | === Slides === | ||
| − | * | + | * William's slides: [http://www.cs.cmu.edu/~wcohen/10-601/nnets.pptx in Powerpoint], [http://www.cs.cmu.edu/~wcohen/10-601/nnets.pdf in PDF] |
=== Readings === | === Readings === | ||
| − | * Mitchell: Ch. 4, | + | * Mitchell: Ch. 4, Murphy Ch 16.5 |
=== 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 |
| − | * | ||
| − | |||
Latest revision as of 16:44, 6 January 2016
This a lecture used in the Syllabus for Machine Learning 10-601B in Spring 2016
Slides
- William's slides: in Powerpoint, in PDF
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
