10-601B Neural networks and Backprop

From Cohen Courses
Revision as of 09:17, 12 January 2016 by Wcohen (talk | contribs) (→‎Slides)
Jump to navigationJump to search

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