Julia Ling
|
CTO
Citrine Informatics |
|
Dr. Julia Ling is the CTO at Citrine Informatics, a 70+ person start up in the Bay Area building an AI platform to accelerate new materials development for a more sustainable future. She's a recognized leader in applying machine learning to scientific applications. She was a Truman Fellow at Sandia National Labs where she helped pioneer the application of deep learning to turbulence modeling. At Citrine, she has led core technology development for applying machine learning to materials and chemicals development. She holds a PhD in Mechanical Engineering from Stanford University and a Bachelors in Physics from Princeton University.
|
Workshop: Machine Learning for Scientific R&D: Why it's Hard and Why it's Fun
Prerequisite: Some familiarity with basic ML concepts, e.g. training data, test data, cross-validation, model training
Why has the pace of adoption of machine learning in scientific R&D been so slow compared to other application areas? This talk will cover some of the key challenges in machine learning for R&D applications: the small, often-messy, sample-biased datasets; the exploratory nature of scientific discovery; and the curious, hands-on approach of scientific users. We will discuss potential solutions to these challenges, including transfer learning, integration of scientific domain knowledge, uncertainty quantification, and machine learning model interpretability. We will walk through illustrative case studies from both turbulence modeling and materials development to show how these challenges and solutions manifest in real-life use cases.
Why has the pace of adoption of machine learning in scientific R&D been so slow compared to other application areas? This talk will cover some of the key challenges in machine learning for R&D applications: the small, often-messy, sample-biased datasets; the exploratory nature of scientific discovery; and the curious, hands-on approach of scientific users. We will discuss potential solutions to these challenges, including transfer learning, integration of scientific domain knowledge, uncertainty quantification, and machine learning model interpretability. We will walk through illustrative case studies from both turbulence modeling and materials development to show how these challenges and solutions manifest in real-life use cases.