This course will cover the fundamental concepts related to Transfer Learning and Deep Learning. Topics include:
Prerequisites: Programming skills up to data structures and a senior/graduate level course in statistics. Knowledge of Python. An intro to ML course is recommended.
Wed 5-8 pm
Deep Learning for Coders with fastai & PyTorch by Howard and Gugger
Ricardo A. Calix, Ph.D.
Purdue University Northwest
rcalix@pnw.edu
My office is at 241 Anderson
Thursday 2-4 pm
Brightspace
You can use Scholar GPUs for Homework assignments.
Labs
We will use the following software:
Mon | Tue | Wed | Thu | Fri |
---|---|---|---|---|
Jan 8 What is Transfer Learning Video |
Jan 9 |
Jan 10 Intro to RLHF (Video)A Hello World GPT (Video) |
Jan 11 |
Jan 12 |
Jan 15 HF: Simple BERT Examples |
Jan 16 | Jan 17 Simple Example of how ChatGPT was trained (Video)HF: Zero Shot BERT classifier (Video) |
Jan 18 | Jan 19 |
Jan 22 Theory of GPTs, BERTs, and Full Transformers (Video 1)
|
Jan 23 |
Jan 24 Theory of GPTs, BERTs, and Full Transformers (Video 2) |
Jan 25 |
Jan 26 |
Jan 29 More HF Examples
|
Jan 30 |
Jan 31 Theory of GPTs, BERTs, and Full Transformers (Video 3)
|
Feb 1 | Feb 2 |
Feb 5 |
Feb 6 |
Feb 7 |
Feb 8 | Feb 9 |
Feb 12 Basics of optimization and gradient descent for ML |
Feb 13 |
Feb 14 Basics of optimization and gradient descent for ML |
Feb 15 | Feb 16 |
Feb 19 Cross Entropy loss, torch.where, and the sigmoid |
Feb 20 |
Feb 21 Cross Entropy loss, torch.where, and the sigmoid |
Feb 22 | Feb 23 |
Feb 26 Intro to fastai |
Feb 27 | Feb 28 |
Feb 29 | Mar 1 |
Mar 4 Machine Learning Basics with PyTorch, fastai, and MNIST Machine Learning Basics with PyTorch, fastai, and MNIST |
Mar 5 |
Mar 6 fastai tabular module fastai examples: image segmentation, text processing, gpu memory issues fastai dataloader and your own image data fastai Bing Search API HW, and Data Ethics with Transformer models |
Mar 7 |
Mar 8 break |
Mar 11 |
Mar 12 |
Mar 13 |
Mar 14 |
Mar 15 |
Mar 18 |
Mar 19 |
Mar 20 |
Mar 21 |
Mar 22 |
Mar 25 |
Mar 26 |
Mar 27 |
Mar 28 | Mar 29 |
Apr 1 |
Apr 2 |
Apr 3 |
Apr 4 | Apr 5 |
Apr 8 |
Apr 9 |
Apr 10 |
Apr 11 | Apr 12 |
Apr 15 |
Apr 16 |
Apr 17 |
Apr 18 | Apr 19 |
Apr 22 Presentations |
Apr 23 |
Apr 24 Presentations |
Apr 25 | Apr 26 |
Apr 29 Finals |
Apr 30 Finals |
May 1 Finals |
May 2 Finals |
May 3 Finals |