This course will cover the fundamental concepts related to machine learning. Topics include:
Prerequisites: Programming skills up to data structures and a senior/graduate level course in statistics. Knowledge of Python and Linux.
Monday 5-8 pm.
Deep Learning with PyTorch by Stevens, Antiga, Viehmann
Ricardo A. Calix, Ph.D.
Purdue University Northwest
rcalix@pnw.edu
My office is at 241 Anderson
Brightspace
Environment:
AWS
WL Scholar
Labs
We will use the following software:
Mon | Tue | Wed | Thu | Fri |
---|---|---|---|---|
Aug 23 Intro to the course |
Aug 24 |
Aug 25 Machine Learning motivation |
Aug 26 |
Aug 27 |
Aug 30 Anaconda and PyTorch |
Aug 31 |
Sep 1 PyTorch basics and the Tensor |
Sep 2 |
Sep 3 |
Sep 6 | Sep 7 |
Sep 8 | Sep 9 |
Sep 10 |
Sep 13 Numpy and PyTorch Interoperability, Reading images into PyTorch |
Sep 14 |
Sep 15 Reading CSV files and text into PyTorch |
Sep 16 |
Sep 17 |
Sep 20 Linear Regression |
Sep 21 |
Sep 22 Linear Regression |
Sep 23 |
Sep 24 |
Sep 27 Simple neural network |
Sep 28 |
Sep 29 Simple neural network |
Sep 30 |
Oct 1 |
Oct 4 CIFAR10 and tensor transformations |
Oct 5 |
Oct 6 CIFAR10 and tensor transformations |
Oct 7 |
Oct 8 |
Oct 11 |
Oct 12 |
Oct 13 |
Oct 14 |
Oct 15 |
Oct 18 Mid-Term Exam
|
Oct 19 |
Oct 20 |
Oct 21 |
Oct 22 |
Oct 25 Performance Metrics |
Oct 26 |
Oct 27 WEKA and sklearn |
Oct 28 |
Oct 29 |
Nov 1 Scraping data from the web: HTML, RSS feeds |
Nov 2 |
Nov 3 |
Nov 4 |
Nov 5 |
Nov 8 Project, VSM, BOW, and SVD |
Nov 9 |
Nov 10 Unsupervised Learning and KMeans |
Nov 11 |
Nov 12 |
Nov 15 SKLearn traditional ML algorithms |
Nov 16 |
Nov 17 SKLearn and UCI datasets |
Nov 18 |
Nov 19 |
Nov 22 Sequential ML - HMM |
Nov 23 |
Nov 24 Sequential ML - HMM |
Nov 25 |
Nov 26 |
Nov 29 Sequential ML - Reinforcement Learning with Q-Learn (chapter) |
Dec 1 |
Dec 2 |
Dec 3 |
Dec 4 |
Dec 7 Project presentations |
Dec 8 |
Dec 9 |
Dec 10 |
Dec 11 |
Dec 14 Finals |
Dec 15 Finals |
Dec 16 Finals |
Dec 17 Finals |
Dec 18 Finals |