Machine Learning

Need help with Machine Learning?

Visit Drop-in Hours or Schedule a Consultation: <link to an embedded google calendar OB widget or google form widget> 

Below are the consultant we have available with Machine Learning and other expertise listed.

Hugh Kadhem

Mathematics

Hugh Kadhem is a Ph.D. student in Applied Mathematics, with broad research interests in computational quantum physics and high-performance scientific computing.

Sand Mining - Plugging a Critical Data Gap

May 14, 2024
Suraj Nair
by Suraj Nair. Excessive sand mining is causing a global ecological crisis. In this blog post, I present why sand mining is one of the most pressing challenges facing the planet, and why persistent data gaps hinder accountability and monitoring. I also discuss an ongoing research project of mine where we combine freely available satellite imagery and machine learning models to build open-source sand mine detection tools that can plug some of these data gaps.

Tactics for Text Mining non-Roman Scripts

April 15, 2024
Hilary Faxon, Ph.D.
by Hilary Faxon, Ph.D. & Win Moe. Non-Roman scripts pose particular challenges for text mining. Here, we reflect on a project that used text mining alongside qualitative coding to understand the politicization of online content following Myanmar’s 2021 military coup.

Computational Social Science in a Social World: Challenges and Opportunities

March 26, 2024
José Aveldanes
by José Aveldanes. The rise of AI, Machine Learning, and Data Science are harbingers of the need for a significant shift in social science research. Computational Social Science enables us to go beyond traditional methods such as Ordinary Least Squares, which face challenges in addressing complexities of social phenomena, particularly in modeling nonlinear relationships and managing high-dimensionality data. This paradigmatic shift requires that we embrace these new tools to understand social life and necessitates understanding methodological and ethical challenges, including bias and representation. The integration of these technologies into social science research calls for a collaborative approach among social scientists, technologists, and policymakers to navigate the associated risk and possibilities of these new tools.

Using Big Data for Development Economics

March 18, 2024
Leïla Njee Bugha
by Leïla Njee Bugha. The proliferation of new sources of data emerging from 20th and 21st century technologies such as social media, internet, and mobile phones offers new opportunities for development economics research. Where such research was limited or impeded by existing data gaps or limited statistical capacity, big data can be used as a stopgap and help accurately quantify economic activity and inform policymaking in many different fields of research. Reduced cost and improved reliability are some key benefits of using big data for development economics, but as with all research designs, it requires thoughtful consideration of potential risks and harms.

Dive into the Future of AI with the LLM Working Group at D-Lab

February 7, 2024
Tom van Nuenen, Ph.D.
by Tom van Nuenen, Celebrating 10 years of innovation in data-intensive social science, D-Lab in collaboration with Grad Div is excited to introduce the LLM Working Group, an initiative focused on the exploration and discussion of Large Language Models (LLMs) like ChatGPT within academic research and teaching. This group aims to unite scholars, students, and data scientists to address crucial questions about AI's role in academia, including access, impact, creativity, and learning in the age of information automation. Through a series of interactive sessions, participants will gain insights into LLM capabilities, discuss ethical considerations, and explore innovative approaches to utilizing these tools in their work. Whether you're an AI veteran or a novice curious about the potentials of GenAI, the LLM Working Group offers a collaborative platform to learn, share, and shape the future of academic inquiry. Join us in navigating the world of LLMs together.

Creating the Ultimate Sweet

January 30, 2024
Emma Turtelboom
by Emma Turtelboom. What is the best Halloween candy? In this blog post, we will identify attributes of popular sweets and create a model to understand how these attributes influence the popularity of the sweet. We’ll discuss alternative model approaches and potential drawbacks, as well as caveats to interpreting the predictions of our model.

Addison Pickrell

IUSE Undergraduate Advisory Board
Mathematics
Sociology

Addison is an aspiring mathematician and social scientist (Class of '27). He loves collecting books he'll never read, is an open-source and open-access advocate, and an aspiring community organizer and systems disrupter. Ask me about community-based participatory action research (CBPAR), critical pedagogy, applied mathematics, and social science.

Tracking Urban Expansion Through Satellite Imagery

December 12, 2023
Leïla Njee Bugha
by Leïla Njee Bugha. Among its many uses, remote sensing can prove especially useful to document changes and trends from eras or settings, where traditional sources are either inexistent or infrequently collected. This is the case when one wants to study urban expansion in sub-Saharan countries over the past 20 years. To further remedy the lack of data on land cover uses from earlier time periods, classification methods can be used as well. Using easily accessible satellite imagery from Google Earth Engine, I provide here an example combining remote sensing with classification to detect changes in the land cover in Nigeria since 2000 due to urban expansion.

Artificial Intelligence and the Mental Health Space: Current Failures and Future Directions

October 31, 2023
María Martín López
by María Martín López. María Martín López, a PhD student in the department of psychology whose research focuses on large language models within the context of mental illness, gives an overview of current failures and possible future directions of NLP models in the mental health space. She brings up questions that must be considered by all researchers working in this space and encourages these individuals to think creatively about the use of AI beyond direct treatment.