# Difference between revisions of "Class meeting for 10-405 Deep Learning"

From Cohen Courses

Jump to navigationJump to search (→Slides) |
|||

Line 14: | Line 14: | ||

* [https://qna.cs.cmu.edu/#/pages/view/79 Quiz for lecture 1] | * [https://qna.cs.cmu.edu/#/pages/view/79 Quiz for lecture 1] | ||

+ | |||

+ | * [https://qna.cs.cmu.edu/#/pages/view/246 Quiz for lecture 2] | ||

* [https://qna.cs.cmu.edu/#/pages/view/212 Quiz for lecture 3] - draft | * [https://qna.cs.cmu.edu/#/pages/view/212 Quiz for lecture 3] - draft |

## Revision as of 18:17, 19 March 2018

This is one of the class meetings on the schedule for the course Machine Learning with Large Datasets 10-405 in Spring 2018.

### Slides

- Lecture 1: Powerpoint, PDF.

- Lecture 2: Powerpoint, PDF (draft)

- Lecture 3: Powerpoint, PDF (draft)

### Quizzes

These are not updated yet --Wcohen (talk) 14:58, 19 March 2018 (EDT)

- Quiz for lecture 3 - draft

### Sample code

### 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 much much 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 (autodiff)
- Wengert lists
- How to evaluate and differentiate a Wengert list

- Common architectures
- Multi-layer perceptron
- Recursive NNs (RNNS) and Long/short term memory networks (LSTMs)
- Convolutional Networks (CNNs)