Home Page
We all share the same reality, yet we each experience it differently. Solving problems collectively is complicated, and poses legitimate ethical concerns, yet collective solutions can be more robust, novel, and inclusive than those solved individually.
The same is true for artificial intelligence. Our lab designs and investigates algorithms that engage, model, and learn from human populations, creating dynamic systems that represent diverse values and beliefs, build trust, and advance community values in public policy and decision making.
Research
Bayelemabaga
We are developing methods to collect, clean data and evaluate and train translation models using crowdsourcing. And are striving to become a national project in Mali as part of its initiative to use science and technology to advance its education and economic development.
Predicting public health risks from first-person narratives
Health and well-being, particularly on a public scale depends greatly on our actions, social and otherwise. Many people around the world spend substantial periods of their lives online.
Diversity-preserving supervised learning
This project addresses basic problems that underlie the our lab’s more application-driven activities.
Our People
Christopher Homan, Ph.D.
Associate Professor
Computer Science
Golisano College of Computing and Information Sciences
News
Paper accepted by the International
Public knowledge and attitudes towards bystander cardiopulmonary resuscitation (CPR) in Ghana, West Africa by Anto-Ocrah, M., Maxwell, N., Cushman, J., Acheampong, E., Kodam, R. S., Homan, C., & Li, T. was excepted by the International Journal of Emergency Medicine.
The 8th International Conference on Learning Representations ICLR in April 2020
Assessing Human Translations from French to Bambara for Machine Learning: a Pilot Study, by LPI MS student Allahsera Auguste Tapo, PI Christopher Homan, and Michael Leventhal, Sarah Luger, and Marcos Zampieri was accepted to the AfricaNLP 2020 workshop, held at the 8th International Conference on Learning Representations ICLR in April 2020.
Neighborhood-based Pooling for Population-level Label Distribution Learning was accepted to ECAI
Neighborhood-based Pooling for Population-level Label Distribution Learning, by LPI Ph.D. students Weerasooriya (lead author) and Liu and PI Homan, was accepted to the 14th European Conference on Artificial Intelligence (ECAI), to be held in Santiago de Compostela, Spain in August 2020.
PI Christopher Homan Presented His Paper in Seventh AAAI Conference
PI Homan presented his paper, Learning to Predict Population-Level Label Distributions Seventh AAAI Conference on Human Computation and Crowdsourcing, coauthored with LPI Ph.D. student Tong Liu (lead author) and LPI MS students Akash Venkatachalam & Pratik Sanjay Bongale.