Cornell University

This seminar is a hybrid event. REGISTRATION REQUIRED for Zoom: https://cornell.zoom.us/meeting/register/tJclceCtrDsjHtNPqTkcNT-hXHcgUTfBE59O

With rapidly growing amounts of experimental data, machine learning is increasingly crucial for automating scientific data analysis. However, many real-world workflows demand expert-in-the-loop attention and require models that not only interface with data, but also with experts and domain knowledge. My research develops full stack solutions that enable scientists to scalably extract insights from diverse and messy experimental data with minimal supervision. My approaches learn from both data and expert knowledge, while exploiting the right level of domain knowledge for generalization. In this talk, I will present progress towards developing automated scientist-in-the-loop solutions, including methods that automatically discover meaningful structure from data such as self-supervised keypoints from videos of diverse behaving organisms. I will also present methods that use these interpretable structures to inject domain knowledge into the learning process, such as guiding representation learning using symbolic programs of behavioral features computed from keypoints. My aim is to enable AI that collaborates with scientists to accelerate the scientific process.

Jennifer is a research scientist at Google, joining Cornell CS as an assistant professor in August 2024. Her research focuses on computer vision and machine learning methods that can be integrated into real-world workflows involving expert-in-the-loop interactions. She aims to accelerate scientific discovery and optimize expert attention in real-world workflows, tackling challenges including annotation efficiency, model interpretability and generalization, and semantic structure discovery. Jennifer received her PhD from Caltech in September 2023. 

The Cornell Institute for Digital Agriculture (CIDA), a faculty led initiative focused on creating a strong voice in the emerging area of Digital Agriculture (DA), invites Jennifer Sun to present her research for CIDA’s monthly seminar series.

Background on the Cornell Institute for Digital Agriculture

An interdisciplinary group of Cornell University faculty began meeting in early 2017 to formulate an Initiative for Digital Agriculture, believing that Cornell is uniquely equipped to lead in this emerging arena that will benefit the public for generations. We define DA to mean the application of computational and information technologies coupled with nanotechnology, biology, systems engineering and economics to both the research and operational sides of agriculture and food production. With approximately 100 faculty from 5 Cornell colleges participating, we are collaborating with external stakeholders to shape and implement a research agenda for DA that will build a pipeline of discovery and innovations for the next 10+ years. Please contact Gabriela Cestero at gc423@cornell.edu with any questions

1 person is interested in this event

User Activity

No recent activity