About this Abstract |
Meeting |
2023 TMS Annual Meeting & Exhibition
|
Symposium
|
AI/Data Informatics: Computational Model Development, Validation, and Uncertainty Quantification
|
Presentation Title |
Intrinsic Dimensionality Estimates for Microstructural Data |
Author(s) |
Megna Shah, Veera Sundararaghavan, Jeff Simmons |
On-Site Speaker (Planned) |
Megna Shah |
Abstract Scope |
Microstructure images, generated by many modalities, contain information about the material, but almost certainly less information than the number of bits they take up on a hard drive. Relatedly, there are a number of established methodologies to estimate the intrinsic dimensionality of data, given a distance or similarity metric. We apply and modify some of these methodologies to estimate the intrinsic dimensionality of various microstructure image datasets with varying distance/similarity metrics, including physics informed metrics. Understanding the dimensionality of a microstructure dataset has numerous implications for choosing latent dimensions in a neural network that will be trained on microstructure data, and ultimately navigating the learned microstructure latent space along those dimensions. |
Proceedings Inclusion? |
Planned: |
Keywords |
ICME, Machine Learning, Characterization |