Difference between revisions of "10-601 Deep Learning 2"

From Cohen Courses
Jump to navigationJump to search
Line 16: Line 16:
 
* [https://cs.stanford.edu/people/karpathy/convnetjs/demo/mnist.html  There's an on-line demo of CNNs] which are trained in your browser (!)
 
* [https://cs.stanford.edu/people/karpathy/convnetjs/demo/mnist.html  There's an on-line demo of CNNs] which are trained in your browser (!)
 
* [http://scs.ryerson.ca/~aharley/vis/conv/  3D visualization of a trained net.]
 
* [http://scs.ryerson.ca/~aharley/vis/conv/  3D visualization of a trained net.]
 +
 +
The LSTM figures and examples I used are mostly from
 +
* [http://colah.github.io/posts/2015-08-Understanding-LSTMs/ Christopher Olah's blog]
 +
* [http://karpathy.github.io/2015/05/21/rnn-effectiveness/ The unreasonable effectiveness of RNNs]
 +
* For a great counterpoint: see [http://nbviewer.jupyter.org/gist/yoavg/d76121dfde2618422139 Yoav Goldberg's response]
  
 
===  Things to remember  ===
 
===  Things to remember  ===

Revision as of 14:22, 11 April 2016

This a lecture used in the Syllabus for Machine Learning 10-601B in Spring 2016

Slides

Readings

This area is moving very fast and the textbooks are not up-to-date. Some recommended readings:

I also used some on-line visualizations in the materials for the lecture, especially the part on ConvNets.

The LSTM figures and examples I used are mostly from

Things to remember

  • Convolutional networks
    • 2-d convolution
    • How to construct a convolution layer
    • Architecture of CNN: convolution/downsampling pairs
Retrieved from "http://curtis.ml.cmu.edu/w/courses/index.php?title=10-601_Deep_Learning_2&oldid=18464"