Courses

Practical Deep Learning

This course will cover the fundamental concepts related to deep 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 for Coders with fastai & PyTorch by Howard and Gugger

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

Office Hours

Thursday 4-6 pm 

About Purdue University Northwest

Code

GitHub
 

Videos

Blackboard (Submit homework on Brightspace)

Brightspace

Related Papers

Lab Environment

Environment:

AWS

Scholar

Course Materials

Labs

  1. More materials on Brightspace

Tools

We will use the following software:

  1. Linux
  2. Python
  3. Anaconda

Calendar Spring 2022 (Subject to change)

Mon Tue Wed Thu Fri

Jan 10

Transfer Learning

video

Jan 11

 

Jan 12

Intro to fastai

video

Jan 13
 
Jan 14
Jan 17 Jan 18 Jan 19 Jan 20 Jan 21

Jan 24

fastai examples: image segmentation, text processing, gpu memory issues

video

Jan 25

Jan 26

fastai examples: text and tabular processing. Huggingface's transformers module

video

Jan 27
 
Jan 28

Jan 31

fastai dataloader and your own image data

video

Feb 1

Feb 2

fastai Bing Search API HW, and Data Ethics with Transformer models

video

Feb 3 Feb 4

Feb 7

Machine Learning Basics with PyTorch, fastai, and MNIST

video

Feb 8

Feb 9

Machine Learning Basics with PyTorch, fastai, and MNIST

video

Feb 10 Feb 11

 

Feb 14

Basics of optimization and gradient descent for ML

video

Feb 15

Feb 16

Basics of optimization and gradient descent for ML

video

Feb 17 Feb 18

Feb 21

Cross Entropy loss, torch.where, and the sigmoid

video

Feb 22

Feb 23

Cross Entropy loss, torch.where, and the sigmoid

video

Feb 24 Feb 25

 

Feb 28

Intro to Transformers

video

Mar 1 Mar 2

Mid-Term Exam
Mar 3 Mar 4
 

Mar 7

Transformers and attention

video

Mar 8
 

Mar 9


Fine tuning transformers

video

Mar 10
 
Mar 11

break
Mar 14

 
Mar 15

 
Mar 16

 
Mar 17

 
Mar 18

 

Mar 21

Transformers for sequence and token classification

video

Mar 22
 

Mar 23
 

fine-tuning for text classification with your own data

video

data

Mar 24
 
Mar 25
 

Mar 28

Word embeddings, encoders, and their connection to BERT

video

Mar 29

Mar 30

BERT pre-training tasks

video

Mar 31 Apr 1

Apr 4

Transformers for semantic text similarity

Apr 5

Apr 6

Transformers: Roberta

Apr 7 Apr 8
 

Apr 11

Exam

Apr 12

Apr 13

Work on Project

Apr 14 Apr 15

Apr 18

Apr 19

Apr 20
 

Apr 21 Apr 22
 

Apr 25

Presentations
 

Apr 26

Apr 27
 

Presentations

Apr 28 Apr 29
 
May 2
Finals
May 3
Finals
May 4
Finals
May 5
Finals
May 6
Finals