no code implementations • 12 May 2023 • Shoieb Ahmed Chowdhury, M. F. N. Taufique, Jing Wang, Marissa Masden, Madison Wenzlick, Ram Devanathan, Alan L Schemer-Kohrn, Keerti S Kappagantula
We combine scanning electron microscopy (SEM) images of 347H stainless steel as training data and electron backscatter diffraction (EBSD) micrographs as pixel-wise labels for grain boundary detection as a semantic segmentation task.
1 code implementation • 15 Jul 2022 • Marissa Masden
We algorithmically determine the regions and facets of all dimensions of the canonical polyhedral complex, the universal object into which a ReLU network decomposes its input space.
no code implementations • 12 Apr 2022 • J. Elisenda Grigsby, Kathryn Lindsey, Marissa Masden
We apply a generalized piecewise-linear (PL) version of Morse theory due to Grunert-Kuhnel-Rote to define and study new local and global notions of topological complexity for fully-connected feedforward ReLU neural network functions, F: R^n -> R. Along the way, we show how to construct, for each such F, a canonical polytopal complex K(F) and a deformation retract of the domain onto K(F), yielding a convenient compact model for performing calculations.
no code implementations • 24 Jul 2020 • Marissa Masden, Dev Sinha
Informed by the basic geometry underlying feed forward neural networks, we initialize the weights of the first layer of a neural network using the linear discriminants which best distinguish individual classes.