Courses

ITS 520 - Applied Machine Learning (with PyTorch)

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.

Time Place

Monday 5-8 pm. 
 

Textbook (Not Required)

Deep Learning with PyTorch by Stevens, Antiga, Viehmann

Instructor

Ricardo A. Calix, Ph.D.
Purdue University Northwest
rcalix@pnw.edu

Office Hours

My office is at 241 Anderson

About Purdue University Northwest

Code

GitHub

GitHub PyTotch

GitHub Numpy

Videos

Brightspace (Submit homework on Brightspace)

Brightspace

Datasets

Lab Environment

Environment:

AWS

WL Scholar

Course Materials

Labs

  1. More materials on Brightspace

Recommendations on sources and products

  1. AI

Tools

We will use the following software:

  1. Linux
  2. Python
  3. Anaconda
  4. Install SEED VM on VirtualBox

Calendar Fall  (Subject to change)

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

video

Sep 2
 
Sep 3
Sep 6 Sep 7
 
Sep 8 Sep 9
 
Sep 10

Sep 13

Numpy and PyTorch Interoperability, Reading images into PyTorch

video

Sep 14
 

Sep 15

Reading CSV files and text into PyTorch

video

Sep 16
 
Sep 17

Sep 20

Linear Regression

video

Sep 21
 

Sep 22

Linear Regression

video

Sep 23
 
Sep 24

 

Sep 27

Simple neural network

video

Sep 28
 

Sep 29

Simple neural network

video

Sep 30
 
Oct 1

Oct 4

CIFAR10 and tensor transformations


video

Oct 5
 

Oct 6
 

CIFAR10 and tensor transformations 

video

Oct 7
 
Oct 8

 
Oct 11

 
Oct 12
 
Oct 13

 
Oct 14
 
Oct 15
 

Oct 18

Mid-Term Exam


 

Oct 19

 

Oct 20

CIFAR10 and Deep Learning

video

Oct 21

 
Oct 22

 

Oct 25

Performance Metrics

video

Oct 26

 

Oct 27

WEKA and sklearn

video
 

Oct 28

 
Oct 29

 

Nov 1

Scraping data from the web: HTML, RSS feeds

video

Nov 2

 

Nov 3

Text and the vector space model

video

Nov 4

 
Nov 5
 

Nov 8

Project, VSM, BOW, and SVD

video

Nov 9
 

Nov 10

Unsupervised Learning and KMeans

video

Nov 11
 
Nov  12

Nov 15

SKLearn traditional ML algorithms

video

Nov 16
 

Nov 17

SKLearn and UCI datasets

video

Nov 18
 
Nov 19
 

Nov 22

Sequential ML - HMM

video

Nov 23
 

Nov 24

Sequential ML - HMM

video

Nov 25
 
Nov 26

Nov 29

Sequential ML - Reinforcement Learning with Q-Learn (chapter)

Dec 1
 

Dec 2
 

Work on project

Dec 3
 
Dec 4
 

Dec 7

Project presentations
Dec 8
 

Dec 9
 

Project presentations
Dec 10
 
Dec 11
 
Dec 14
Finals
Dec 15
Finals
Dec 16
Finals
Dec 17
Finals
Dec 18
Finals