no code implementations • 29 Sep 2023 • Burak Boyacıoğlu, Mahnoush Babaei, Amanuel H. Mamo, Sarah Bergbreiter, Thomas L. Daniel, Kristi A. Morgansen
Systems in nature are stochastic as well as nonlinear.
no code implementations • 6 Jun 2022 • Burak Boyacıoğlu, Alice C. Schwarze, Bingni W. Brunton, Kristi A. Morgansen
The neural encoding by biological sensors of flying insects, which prefilters stimulus data before sending it to the central nervous system in the form of voltage spikes, enables sensing capabilities that are computationally low-cost while also being highly robust to noise.
1 code implementation • 16 Mar 2022 • Trevor Avant, Kristi A. Morgansen
We show that this measure is a type of Lipschitz constant, and that it is bounded by the product of a network's Euclidean Lipschitz constant and an intrinsic property of a rotation parameterization which we call the "distance ratio constant".
no code implementations • 27 May 2021 • Natalie Brace, Kristi A. Morgansen
In certain systems which are subject to significant constant external forcing such as an airplane in wind or an underwater glider in ocean currents, the ability to detect the forcing depends on both the measurements available and whether appropriate control is being applied.
1 code implementation • 29 Apr 2021 • Trevor Avant, Kristi A. Morgansen
In this paper, we determine analytical upper bounds on the local Lipschitz constants of feedforward neural networks with ReLU activation functions.
no code implementations • 14 Aug 2020 • Trevor Avant, Kristi A. Morgansen
In this paper, we determine analytical bounds on the local Lipschitz constants of of affine functions composed with rectified linear units (ReLUs).