AI for Scientists: Accelerating Discovery through Knowledge, Data & Learning
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. I work closely with domain experts, such as behavioral neuroscientists, to integrate these methods in real-world workflows. My aim is to enable AI that collaborates with scientists to accelerate the scientific process.
Jennifer is a PhD candidate in Computing and Mathematical Sciences at Caltech, advised by Professors Pietro Perona and Yisong Yue. Her research focuses on developing scientist-in-the-loop computational systems that automatically convert experimental data into insight with minimal expert effort. 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. Beyond her research work, she has organized multiple workshops to facilitate connections across fields at top AI conferences, such as CVPR, and she has received multiple awards, such as best student paper at CVPR 2021.