Transforming Your Research with Generative AI
If you are a U-M researcher looking to learn more about when, why, and how to integrate generative AI tools into your research, please register to join us at one of our upcoming sessions.
The Fall 2024 series, co-hosted by Michigan Medicine, is open to all U-M researchers. Additionally, if you are unable to attend in person, recordings of the sessions will be available for later viewing.
No prior experience with generative AI tools is required. Participants will need to supply their own laptop for each session.
Series co-organizer
Upcoming Sessions & Registration
Location: Unless otherwise noted, all sessions will take place at the Medical Science Building II North Lecture Hall (1137 Catherine St, Ann Arbor MI 48109).
About: This session will introduce you to some useful ways to incorporate Generative AI tools in your research, including a brief outline of tools and topics to be covered in depth in the subsequent sessions. It will also include an introduction to prompting with ChatGPT.
Instructor: Dr. James Boyko, Schmidt AI in Science Postdoctoral Fellow, Michigan Institute for Data Science
RegisterAbout: This session will present current discussions on governance and infrastructure for integrating generative AI tools into research and clinical operations at Michigan Medicine, including guidelines for using specific generative AI tools with sensitive data.
Instructors: Michael Burns, Erin Kaleba, Karl Renius, Kayvan Najarian, Carleen Penoza, Ranjit Aiyagari, Steve Kunkel, Brahmajee Nallamothu, Michael Sjoding, Andrew Krumm, Brian Athey
Past Sessions
About: This session on using generative AI for data visualization is tailored for participants with a background in R. Basic familiarity with R syntax, reading in and manipulating data, installing packages from CRAN or GitHub, and basic knowledge of writing custom functions will be helpful. We will focus on practical examples of leveraging LLM tools in data visualization workflows, including an overview of the principles of data visualization and a discussion of GPT models for writing code and data exploration.
Note: Access to and familiarity with R/RStudio is required for the hands-on exercises. We recommend a local installation (https://www.r-project.org/, https://posit.co/download/rstudio-desktop/), but a browser-based Windows virtual environment is available through UM Virtual Sites (U-M login required). A list of needed packages will be provided before the workshop.
Instructor: Dr. Jacob Berv, Schmidt AI in Science Fellow, Michigan Institute for Data and AI in Society
View Recording View MaterialsAbout: Dr. Juan B. Gutiérrez, Professor and Chair of Mathematics at the University of Texas at San Antonio, will guide participants on how to constrain ChatGPT through custom instructions to maximize the likelihood of obtaining scientifically correct answers to your queries, with a focus on reproducibility. Develop (or hone) your ChatGPT skills developing an analysis pipeline for a real dataset that will teach you something you maybe did not know about your own community in the US (the 2018 Civil Rights Dataset from the Department of Education). There will be step-by-step tutorials, or open exploration suggested for beginner, intermediate, and advanced participants; the only prerequisite is to bring a laptop. The techniques applied in this workshop can be re-deployed in research projects in multiple domains. Participants can have ChatGPT write their manuscripts for peer-review using this rich dataset.
Instructor: Juan Gutiérrez, Professor and Chair of Mathematics, University of Texas at San Antonio
View RecordingAbout: In this open-ended session, we will try to get ChatGPT, Claude, and other LLMs to generate code and graphics — both classically in R and Bayesianly in Stan — for some of the most common models run in the social and physical sciences, starting with standard regression and working our way up to various nonlinear models (e.g., GAMs, GPs), time-series / panels, and discrete choices (e.g., binary and multinomial logit). The emphasis will be on data exploration, generalizing code to relax assumptions underlying more computationally simple models, and locating bottlenecks in existing code.
Note for participants: Bring your laptop! This session will include use of custom GPTs, accessible through ChatGPT Plus ($20/monthly). Test data will be distributed in advance, but participants can bring some of their own to see if we can analyze it collectively in real-time. It is recommended, but optional, to have RStudio installed on your own laptop or to be able to run it remotely (e.g., on Great Lakes).
Instructor: Fred Feinberg, Joseph Handleman Professor, Professor of Marketing, Stephen M Ross School of Business and Professor of Statistics, College of Literature, Science, and the Arts
View Recording View MaterialsAbout: This session introduced generative AI tools that can assist you with literature discovery, summarization, and synthesis. Featured tools include Open AI’s chatGPT, UMGPT, Anthropic’s Claude, ResearchRabbit, and more.
Instructors:
Jamie Niehof, Engineering Librarian
Tyler Nix, Associate Director, Research & Informatics, Taubman Health Sciences Library
Sarah Barbrow, Assistant Director, Engineering Librarian
About: This session will introduce you to using ChatGPT and other tools for academic writing, including topics such as drafting communications, making posters and presentations, brainstorming ideas, and organizing notes.
Instructor: Stephanie Moody, Lecturer II, English Department and Sweetland Center for Writing
View SlidesAbout: attendees learned about generative AI tools for working with text data, including creating and analyzing data from a variety of sources; discussion of benefits, capabilities, and challenges including how to assess bias. Hands-on exercises focused on real-world examples using text data. Instructor Dr. Mark Hansen was the inaugural director for the David and Helen Gurley Brown Institute of Media Innovation and is a data scientist at Columbia University working at the intersection of data, art and technology. His work has appeared in the Museum of Modern Art in New York, the Whitney Museum, and the lobby of the New York Times.
Instructor: Mark Hansen, David and Helen Gurley Brown Professor of Journalism and Innovation; Director, David and Helen Gurley Brown Institute of Media Innovation, Columbia Journalism School, and Professor, Department of Statistics
View Recording View Slides View G-Colab 1 View G-CoLab 2About: This session will introduce you to some useful ways to incorporate Generative AI tools in your research, including a brief outline of tools and topics to be covered in depth in the subsequent sessions. It will also include an introduction to prompting with ChatGPT.
Instructor: James Boyko, Schmidt AI in Science Postdoctoral Fellow, Michigan Institute for Data and AI in Society
View Recording View SlidesMaking Generative AI Better for You: Fine-tuning and Experimentation for Custom Research Solutions – Shane Storks, Graduate Student Research Assistant, Computer Science and Engineering, College of Engineering
View Recording View SlidesTutorial: Fine-tuning LLMS – Shane Storks, Graduate Student Research Assistant, Computer Science and Engineering, College of Engineering
View Recording MaterialsGenerative Image Models in Research – Jeong Joon Park, Assistant Professor of Electrical Engineering and Computer Science, College of Engineering
View SlidesTutorial: Generative Adversarial Networks (GANs) – Anthony Carreon, Graduate Student Research Assistant, Aerospace Engineering, College of Engineering
MaterialsUsing Generative AI to Enhance Coding in Research – Sindhu Kutty, Lecturer IV in Electrical Engineering and Computer Science, College of Engineering
View Recording MaterialsTutorial: Using Generative AI to Improve Your Code (focusing on Python but applicable to other languages too) – Qiyuan Zhao, Research Fellow, Medicinal Chemistry, College of Pharmacy
View Recording MaterialsEthical Considerations for Using Generative AI in Research – H. V. Jagadish, Edgar F Codd Distinguished University Professor of Electrical Engineering and Computer Science, Bernard A Galler Collegiate Professor of Electrical Engineering and Computer Science, Professor of Electrical Engineering and Computer Science, College of Engineering; Director of the Michigan Institute for Data and AI in Society
View SlidesTutorial: Using Generative AI to Enhance Research Workflows – James Boyko, Schmidt AI in Science Postdoctoral Fellow, Michigan Institute for Data and AI in Society
View SlidesQuestions? Contact Us.
Questions? Please reach out to Kelly Psilidis (MIDAS Faculty Training Program Manager) at psilidis@umich.edu.