Difference between revisions of "10-601B Neural networks and Backprop"
From Cohen Courses
Jump to navigationJump to search (→Slides) |
(→Slides) |
||
| Line 3: | Line 3: | ||
=== Slides === | === Slides === | ||
| − | * ... | + | * [http://curtis.ml.cmu.edu/w/courses/images/8/8b/Kernelized-svms.pdf Kernelized svm slides in pdf] |
| + | * [http://curtis.ml.cmu.edu/w/courses/images/a/aa/Kernelized-svms.pptx Kernelized svm slides in ppt] | ||
=== Readings === | === Readings === | ||
Latest revision as of 22:06, 8 February 2016
This 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
