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 2-5 pm. 
 

Textbook

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
 

Videos

Brightspace (Submit homework on Brightspace)

Brightspace

Datasets

Lab Environment

Environment:

AWS

WL Scholar

Course Materials

Labs

  1. More materials on Brightspace

Tools

We will use the following software:

  1. Linux
  2. Python
  3. Anaconda

Calendar Fall 2021 (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 19

Mid-Term Exam


 

Oct 20

 

Oct 21

CIFAR10 and Deep Learning

Oct 22

 
Oct 23

 

Oct 26



 

Oct 27

 

Oct 28


 

Oct 29

 
Oct 30

 

Nov 2

Tensorflow 2.0 basics

Nov 3

 

Nov 4

Tensorflow 2.0 basics and intro to Keras

Nov 5

 
Nov 6
 

Nov 9

Tensorflow 2.0 Tensor operations and the dataset module

Nov 10
 

Nov 11

Tensorflow 2.0 Loading images and tfds

Nov 12
 
Nov  13

Nov 16

XOR problem in Tensorflow 2.0 and Keras

Nov 17
 

Nov 18

Tensorflow 2.0 and Keras 
Nov 19
 
Nov 20
 

Nov 23

Re-inforcement Learning with Q-Learn (chapter)

Nov 24
 

Nov 25

Re-inforcement Learning with Q-Learn

Nov 26
 
Nov 27

Nov 30

Unsupervised Learning (clustering with KMeans)

Dec 1
 

Dec 2
 

Unsupervised Learning (compression with Singular Value Decomposition (SVD) and clustering)

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