Unit 13: Generation and Miscellaneous Topics

The main objective of the rest of our time together is to understand how, at a high level, how AI models can generate dialogues, code, images, and other kinds of data.

We’ll also mention some other topics that you should be aware of, but that we won’t have time to cover in detail.

Objectives

(By “work”, I mean, how do they use the building blocks of neural networks, which we’ve studied so far, to generate data.)

Supplemental Objectives

Here are a few more things that would be helpful to know about, even though they’re not the main focus of this class:

Reading

Please read the following sometime before the last day of class:

Background

Review my blog post on Mapping to Mimicry. I wrote it in one short sprint; feedback welcome!

Generative Models

The Illustrated Stable Diffusion – Jay Alammar – Visualizing machine learning one concept at a time.

Robotics

Rather than study theory, let’s look at two recent blog advances:

Explainable and Human-Centered AI

ACM Selects: Trustworthy AI in Healthcare #02

Supplemental

What happens when AI meets people? How can we ensure that AI results are:

The first two are the subject of a subfield called Fairness, Accountability, and Transparency; the last is the subject of much research in human-computer interaction (HCI) and computer-supported cooperative work (CSCW). We’ll explore all three in these last two weeks of class.

Correctness and Transparency / Explainability

Read one or more of these:

Watch:

Supplemental Material

Justice (Fairness, Bias)

Supplemental: The Effects of Regularization and Data Augmentation are Class Dependent | Abstract

Usability

Read or watch something from Human-Centered Artificial Intelligence.

Class Meetings

No Class Monday (Easter Monday)

Wednesday

Generating images

Friday

Lab: generation: autoregressive, GAN, diffusion.

Monday

Interpretability and Explanation (slides)

Wednesday

Fairness and Wrap-Up slides

Final Discussion topics

Thursday: Midterm 2

Contents