Difference between revisions of "Class meeting for 10-605 Deep Learning"
From Cohen Courses
Jump to navigationJump to searchLine 9: | Line 9: | ||
* Automatic differentiation: | * Automatic differentiation: | ||
− | ** William's notes on [http://www.cs.cmu.edu/~wcohen/10-605/notes/autodiff.pdf automatic differentiation], and the | + | ** William's notes on [http://www.cs.cmu.edu/~wcohen/10-605/notes/autodiff.pdf automatic differentiation], and the Python code for a simple [http://www.cs.cmu.edu/~wcohen/10-605/code/xman.py Wengart list generator] and a [http://www.cs.cmu.edu/~wcohen/10-605/code/sample-use-of-xman.py sample use of a one]. |
** [https://justindomke.wordpress.com/2009/03/24/a-simple-explanation-of-reverse-mode-automatic-differentiation/ Domke's blog post] - clear but not much detail - and [http://colah.github.io/posts/2015-08-Backprop/ another nice blog post]. | ** [https://justindomke.wordpress.com/2009/03/24/a-simple-explanation-of-reverse-mode-automatic-differentiation/ Domke's blog post] - clear but not much detail - and [http://colah.github.io/posts/2015-08-Backprop/ another nice blog post]. | ||
** The clearest paper I've found is [http://www.bcl.hamilton.ie/~barak/papers/toplas-reverse.pdf Reverse-Mode AD in a Functional Framework: Lambda the Ultimate Backpropagator] | ** The clearest paper I've found is [http://www.bcl.hamilton.ie/~barak/papers/toplas-reverse.pdf Reverse-Mode AD in a Functional Framework: Lambda the Ultimate Backpropagator] |
Revision as of 17:27, 17 October 2016
This is one of the class meetings on the schedule for the course Machine Learning with Large Datasets 10-605 in Fall_2016.
Slides
- TBD
Readings
- Automatic differentiation:
- William's notes on automatic differentiation, and the Python code for a simple Wengart list generator and a sample use of a one.
- Domke's blog post - clear but not much detail - and another nice blog post.
- The clearest paper I've found is Reverse-Mode AD in a Functional Framework: Lambda the Ultimate Backpropagator
- More general neural networks:
- Neural Networks and Deep Learning An online book by Michael Nielsen, pitched at an appropriate level for 10-601, which has a bunch of exercises and on-line sample programs in Python.
For more detail, look at the MIT Press book (in preparation) from Bengio - it's very complete but also fairly technical.
Things to remember
- The underlying reasons deep networks are hard to train
- Exploding/vanishing gradients
- Saturation
- The importance of key recent advances in neural networks:
- Matrix operations and GPU training
- ReLU, cross-entropy, softmax
- How backprop can be generalized to a sequence of assignment operations