ECE 57000: Artificial Intelligence (Fall 2020)

Important Links

• Syllabus (pdf), tentative course schedule (pdf), and prerequisite quiz (ungraded, also on Gradescope)
• Brightspace (All video links and grades) - For the first time logging into Piazza, Gradescope, or Circuit, please click the links in Brightspace under “Content” and then under the module “Piazza, Gradescope, and Circuit Links”. This will help link your Purdue account with these external learning tools. After the first time, you can just use the links below.
• Piazza (Announcements and discussion)
• Gradescope (Quizzes and assignment submission)
• Circuit (Project checkpoint submission and peer reviews)
• Google Colab (Free computing environment including GPUs)
• Live Zoom, office hour, and recorded video links: See Brightspace

Project Checkpoints

• Course project description (pdf)
  • Due 9/4/2020 (noon, EDT): Checkpoint 1 Instructions (pdf); Checkpoint 1 LaTeX example (zip)
  • Due 9/18/2020 (noon, EDT): Checkpoint 2 Instructions (pdf)
  • Due 10/2/2020 (noon, EDT): Checkpoint 3 Instructions (pdf)
  • Due 10/16/2020 (noon, EDT): Checkpoint 4 Instructions (pdf)
  • Final project and presentation logistics
    • Due 11/9/2020 11/11/2020 (noon, EDT): Term paper (Circuit AND Gradescope)
    • Due 11/13/2020 (noon, EDT): Code zip and 5-min video link (Gradescope)
    • Due 11/13/2020 (noon, EDT): Sign up for presenter and discussant slot
    • Due 12/04/2020 (noon, EDT): In-depth peer reviews

Optional textbooks

The bracketed acronym is used for referencing these books.

1. [DL] Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville, 2016. http://www.deeplearningbook.org
2. [ML] Machine Learning: A Probabilistic Perspective by Kevin P. Murphy, 2012. https://ebookcentral.proquest.com/lib/purdue/detail.action?docID=3339490
3. [PY] Python Data Science Handbook by Jake VanderPlas, 2016. https://jakevdp.github.io/PythonDataScienceHandbook/

Lecture content by week

1. Week 1 (8/24/2020) - Introduction to artificial intelligence
   • Monday: See syllabus, course schedule, and course project links above.
   • Wednesday: Syllabus and AI introduction, How to select a paper, Overview of AI topics
   • Friday: Overview of AI topics, Principal Components Analysis (PCA)
2. Week 2 (8/31/2020) - PCA and linear algebra
   • Monday: Review of linear algebra (notebook, pdf); Related reading: DL, Ch.2
   • Wednesday: Continued from above. See updated PCA slides above.
   • Friday: See updated PCA notes above; PCA demo (notebook, pdf )
3. Week 3 (9/7/2020) - Introduction to machine learning
   • Monday: Intro. to ML; Optional related reading: DL, Ch. 5.1
   • Wednesday: See updated Intro to ML above; K-nearest neighbors (KNN) and evaluating ML methods, (pdf); KNN Demo (notebook, pdf; Optional related reading: KNN Classifier Notes, DL, Ch. 5.2-5.3
   • Friday: See updated KNN notes above.
4. Week 4 (9/14/2020) - Linear models and gradient descent
   • Monday: Linear and Logistic Regression; Optional related reading: PY, Linear regression, DL, Ch. 5.1.4 (short), ML, Ch. 7 and Ch. 8 (in-depth)
   • Wednesday: Gradient Descent; Gradient descent demo (notebook, pdf; Optional related reading: ML, Ch. 8 section 8.3
   • Friday: Gradient descent continued; Loss functions and regularization
5. Week 5 (9/21/2020) - Basics of deep learning
   • Monday: Basics of deep learning
   • Wednesday: PyTorch and automatic differentiation (notebook, pdf)
   • Friday: Basics of convolutional neural networks (CNN); Convolutions demo (notebook, pdf); Optional related reading: DL, Ch. 9
6. Week 6 (9/28/2020) - Clustering
   • Monday: Finish CNNs; CIFAR-10 demo (notebook, pdf);
   • Wednesday: K-means clustering (notebook, pdf);
   • Friday: Spectral clustering; Optional related reading: ML, Ch 25.4.3
7. Week 7 (10/5/2020)
   • Monday: Spectral clustering continued; Review of probability; Optional related reading: DL, Ch. 3, ML, Ch. 2
   • Wednesday: Review of probability (continued); Optional related reading: see above.
   • Friday: Review of probability (continued); updated slides above
8. Week 8 (10/12/2020) Density estimation and GMMs
   • Monday: Density estimation
   • Wednesday: Density estimation (continued);
   • Friday: Gaussian Mixture Model and EM Algorithm; Optional related reading: ML, Ch. 11
9. Week 9 (10/19/2020) Autoencoders, VAE and GANs
   • Monday: Recap GMM/EM, Autoencoders and VAEs; Optional related reading: Original VAE paper (2013), Recent introduction to VAEs by original authors (2019)
   • Wednesday: Autoencoders and VAEs continued (updated slides above)
   • Friday: Generative Adversarial Networks (GAN); Optional related reading: Original GAN paper
10. Week 10 (10/26/2020) Generative Adversarial Networks (continued)
    • Monday: GANs and theory (continued)
    • Wednesday: GANs and theory (continued)
    • Friday: Deep Convolutional GAN (DCGAN); DCGAN MNIST tutorial (notebook, pdf)
11. Week 11 (11/2/2020) Normalizing Flows
    • Monday: No in-person/live lecture; Pre-recorded lecture will be posted Normalizing Flows; Change of variables demo (notebook, pdf)
    • Wednesday: No lecture because reading day
    • Friday: Normalizing flows (continued)
12. Week 12 (11/9/2020) Iterative flows and language modeling
    • Monday: Iterative flows via density destructors
    • Wednesday: Density destructors continued
    • Friday: Topic models
13. Week 13 (11/16/2020) Project presentations
14. Week 14 (11/23/2020) Word embeddings (Thanksgiving week)
    • Monday (optional): Word embeddings (Word2Vec)