Washington University (in St. Louis) Course T81-558: Applications of Deep Neural Networks
Clone or download
Latest commit 6fc1322 Jan 15, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
assignments Updates for Python 3.7 Jan 15, 2019
data Moved data files to data site. Jan 1, 2019
images Fixed figure issue noted by issue #8 Aug 13, 2018
pdf Update room Jan 16, 2019
.gitignore Small cleanup Jul 29, 2018
LICENSE Initial commit Jul 31, 2016
README.md Update room Jan 16, 2019
citations.ipynb Update citations. Dec 30, 2018
datasets_iris.ipynb Fixed a few links. Oct 13, 2018
datasets_mpg.ipynb Fixed a few links. Oct 13, 2018
datasets_toy1.ipynb Adding datasets Aug 28, 2016
datasets_wcbc.ipynb Fixed a few links. Oct 13, 2018
jeffs_helpful.ipynb Update course to latest tensorflow, keras, sklearn Dec 15, 2018
t81_558_class01_intro_python.ipynb Updates for Python 3.7 Jan 15, 2019
t81_558_class02_python_ml.ipynb Fixed several typos and formatting issues. Jan 5, 2019
t81_558_class03_tensor_flow.ipynb Fixed several typos and formatting issues. Jan 5, 2019
t81_558_class04_training.ipynb fixed formatting. Jan 7, 2019
t81_558_class05_class_reg.ipynb Fixed several typos and formatting issues. Jan 5, 2019
t81_558_class06_backpropagation.ipynb Fixed several typos and formatting issues. Jan 5, 2019
t81_558_class07_cnn.ipynb Fixed several typos and formatting issues. Jan 5, 2019
t81_558_class08_kaggle.ipynb Fixed several typos and formatting issues. Jan 5, 2019
t81_558_class09_regularization.ipynb Fixed several typos and formatting issues. Jan 5, 2019
t81_558_class10_lstm.ipynb Fixed several typos and formatting issues. Jan 5, 2019
t81_558_class11_text_nlp.ipynb Fixed several typos and formatting issues. Jan 5, 2019
t81_558_class12_security.ipynb Fixed several typos and formatting issues. Jan 5, 2019
t81_558_class13_adv.ipynb Fixed several typos and formatting issues. Jan 5, 2019
t81_558_class14_aws.ipynb Added additional timings for GPU Jan 13, 2019
t81_558_reference.ipynb Update course to latest tensorflow, keras, sklearn Dec 15, 2018
tf_kdd99.ipynb merged security info Dec 23, 2017

README.md

T81 558:Applications of Deep Neural Networks

Washington University in St. Louis

Instructor: Jeff Heaton

The content of this course changes as technology evolves, to keep up to date with changes follow me on GitHub.

Spring 2019, Mondays, 6-8:30, Online and in class room: Eads Hall / 215

Course Description

Deep learning is a group of exciting new technologies for neural networks. Through a combination of advanced training techniques and neural network architectural components, it is now possible to create neural networks of much greater complexity. Deep learning allows a neural network to learn hierarchies of information in a way that is like the function of the human brain. This course will introduce the student to computer vision with Convolution Neural Networks (CNN), time series analysis with Long Short-Term Memory (LSTM), classic neural network structures and application to computer security. High Performance Computing (HPC) aspects will demonstrate how deep learning can be leveraged both on graphical processing units (GPUs), as well as grids. Focus is primarily upon the application of deep learning to problems, with some introduction mathematical foundations. Students will use the Python programming language to implement deep learning using Google TensorFlow and Keras. It is not necessary to know Python prior to this course; however, familiarity of at least one programming language is assumed. This course will be delivered in a hybrid format that includes both classroom and online instruction.

Objectives

  1. Explain how neural networks (deep and otherwise) compare to other machine learning models.
  2. Determine when a deep neural network would be a good choice for a particular problem.
  3. Demonstrate your understanding of the material through a final project uploaded to GitHub.

Syllabus

This syllabus presents the expected class schedule, due dates, and reading assignments. Download current syllabus.

Module Content
Module 1
Meet on 01/14/2019
  • Python Preliminaries
  • We will meet on campus this week! (first meeting)
Module 2
Week of 01/28/2019
Module 3
Week of 02/04/2019
Module 4
Week of 02/11/2019
Module 5
Meet on 02/18/2019
  • Classifcation and Regression
  • Module 4 Assignment due: 02/19/2019
  • We will meet on campus this week! (2nd Meeting)
Module 6
Week of 02/25/2019
Module 7
Meet on 03/04/2019
  • Convolutional Neural Networks and Computer Vision
  • Module 6 Assignment due: 03/05/2019
  • Current topics pt 1 due 03/05/2019
  • We will meet on campus this week! (3rd Meeting)
Module 8
Week of 03/18/2019
Module 9
Week of 03/25/2019
Module 10
Week of 04/01/2019
Module 11
Week of 04/08/2019
Module 12
Meet on 04/15/2019
  • Security and Deep Learning
  • Kaggle Assignment due: 04/16/2019 (approx 4-6PM, due to Kaggle GMT timezone)
  • We will meet on campus this week! (4th Meeting)
Module 13
Week of 04/22/2019
  • Current topics pt 2 due 04/23/2019
  • Advanced/New Deep Learning Topics
Module 14
Week of 04/29/2019
  • GPU, HPC and Cloud
  • Final Project due 04/30/2019

Datasets

  • Iris - Classify between 3 iris species.
  • Auto MPG - Regression to determine MPG.
  • WC Breast Cancer - Binary classification: malignant or benign.
  • toy1 - The toy1 dataset, regression for weights of geometric solids.

Note: Other datasets may be added as the class progresses.

Final Project

For the final project you can choose a security project or choose your own dataset to create and fit a neural network. For more information:

  • Security Project - See Canvas for more information.
  • Independent Project - Choose your own dataset or one of my suggestions.

Other Information