4 papers
On Making -Invariant Networks Optimal
Tomas Karella, Emily Shinkle, Alice Elisabeth Anastasia Allen +3
Respecting a-priori known symmetries of underlying data is a key principle in designing efficient neural architectures. Convolutional neural networks are a canonical example, encod…
The Truth, the Whole Truth, and Nothing but the Truth: Automatic Visualization Evaluation from Reconstruction Quality
Roxana Bujack, Li-Ta Lo, Ethan Stam +2
Recent advances in AI enable the automatic generation of visualizations directly from textual prompts using agentic workflows. However, visualizations produced via one-shot generat…
Optimal Invariant Bases for Atomistic Machine Learning
Alice E. A. Allen, Emily Shinkle, Roxana Bujack +1
The representation of atomic configurations for machine learning models has led to the development of numerous descriptors, often to describe the local environment of atoms. Howeve…
Flexible Moment-Invariant Bases from Irreducible Tensors
Roxana Bujack, Emily Shinkle, Alice Allen +2
Moment invariants are a powerful tool for the generation of rotation-invariant descriptors needed for many applications in pattern detection, classification, and machine learning.…