AI x Science Seminars
The AI x Science Seminar Series delves into the profound ways artificial intelligence is reshaping scientific discovery and innovation. Join the Penn Community as we explore the tools, breakthroughs, and ethical considerations at the forefront of AI-powered scientific research.
Upcoming AI x Science Seminars
AI x Science Seminar: Pranam Chatterjee
Designing Programmable Molecules with Generative Sequence Models
Amy Gutman Hall, Room 414
The Chatterjee Lab at the University of Pennsylvania develops generative algorithms to design functional molecules directly from sequence. Our work begins with a question: can short peptides be de novo designed to bind undruggable targets like disordered oncogenic fusions…
Past AI x Science Seminars
AI x Science Seminar: Bhuv Jain
Machine Learning in Cosmology
Amy Gutman Hall, Room 414
Professor Jain will describe how we map dark matter from large surveys of galaxies via gravitational lensing. Testing theories of cosmology with maps of galaxies and dark matter is a rich area for machine learning. He will describe the ‘old-fashioned’ physics-based approaches and…
AI x Science Seminar: René Vidal
Learning dynamics in the feature-learning regime: implicit bias, robustness, and low-rank adaptation
Amy Gutman Hall
Room 414
This talk will present new insights into the learning dynamics of gradient flow in the feature-learning regime. For separable data, we show that gradient flow learns a simple ReLU network with two neurons corresponding to the two classes. For data drawn from an orthogonal…
AI x Science Seminar: Eva Dyer
Building unified models of neural data across tasks, modalities, & species
Amy Gutmann Hall, Room 414
Neural activity is complex, dynamic, nonlinear, and high-dimensional, and the datasets we collect from the brain are equally varied. This richness makes analysis difficult, and models trained on narrow conditions rarely generalize. Rather than seeking to simplify the problem, we…
AI x Science Seminar: Nat Trask
Geometric and physics structure preservation in scientific machine learning
Amy Gutman Hall, Room 414
In scientific machine learning, researchers construct simulators of physical systems which are either computationally expensive or intractable to model with conventional simulation tools. Despite impressive steps in the last couple years, these techniques generally fail to meet…
AI × Science Seminar: Jacob Gardner
Extracting knowledge priors from scientific texts for de novo molecular design
Amy Gutman Hall
Room 414
This talk will explore a large-scale effort to exploit the natural-language understanding capabilities of large language models in order to unlock information about the structure, function, and biological activity for proteins, small molecules, genetic variants, and other…
AI for Science Seminar: "A Foundation Model for the Earth System"
AGH 414
Reliable forecasts of the Earth system are crucial for human progress and safety from natural disasters. Artificial intelligence offers substantial potential to improve prediction accuracy and computational efficiency in this field, however this remains underexplored in many…
AI for Science Seminar: Learning as Manifold Packing
Amy Gutmann Hall
Room 414
This talk will explore how concepts from statistical and soft matter physics can be leveraged to analyze neural manifold packing dynamics under stochastic gradient descent and related optimization algorithms.
Join us for the first AI for Science Seminar!
Closing the Gap Between Scientific Foundation Models and Real-World Applications
Amy Gutmann Hall
Room 414
This talk is motivated by recent triumphs in weather and climate modeling, and discusses potentials, breakthroughs, and remaining challenges in fluid dynamics and related engineering fields.
