FYS: Artificial Intelligence in Healthcare
Welcome to the course homepage for the UMass First Year Seminar: Artificial Intelligence in Healthcare! On this page you can find information about the course, and links to course lectures and resources. This page is in development, so check back often for updates.
The first year seminar is intended to be an exploration of computer science for first-year CS majors and exploratory track students where we focus on a single topic. In this section we will discuss artificial intelligence (AI) in healthcare. We will use topics in healthcare to introduce concepts in AI and talk about how different methods in AI have made an impact in healthcare. We will also discuss the topics related to deploying AI models in healthcare, such as interpretability and bias.
Where: Hasbrouck Laboratory Addition Room 107
- Section 3: Tuesdays 4:00 - 5:00 PM
- Section 5: Tuesdays 5:30 - 6:30 PM
Course Instructor: John Lalor
- Email: email@example.com
- Office: CS Building Room 216
- Office hours:
- Tuesdays 2:30pm-3:30pm CS 216
- Tuesdays 5:00pm-5:30pm Hasbrouck 107
Course website: http://jplalor.github.io/fys18.html
Consult the course website for up-to-date course information and lecture slides.
The course syllabus can be accessed here (Updated 09/04/2018).
Below is a rough outline of the topics that we'll cover in class. A typical class meeting will consist of about 30 minutes of lecture introducing one of the topics below, followed by a 20-25 minute activity related to the topic.
- Supervised learning
- Unsupervised learning
- Natural language processing
- Ethics of AI
- AI interpretability
- Standards and ontologies
- Clinical reasoning and probabilistic inference
- Causal inference
There will also be content that is shared among the FYS sections. Once that is finalized it will be added to the schedule.
- 09/04: Course introduction
- 09/11: Definitions and examples (slides)
- 09/18: Supervised learning pt. 1
- 09/25: Supervised learning pt. 2 (slides)
- 10/02: Unsupervised learning pt. 1 (slides)
- 10/16: Unsupervised learning pt. 2 (slides)
- 10/23: Interpretability (slides)
- 10/30: Ethics in ML (slides)
- 11/06: Guest lecture: Diversity in CS
- 11/13: Introduction to probability
- 11/20: No class (Thanksgiving break)
- 11/27: Class cancelled
- 12/04: Graphical models (slides courtesy of Kevin Small and Byron Wallace)