no code implementations • 16 Dec 2021 • C. Sinan Güntürk, Weilin Li
The celebrated universal approximation theorems for neural networks roughly state that any reasonable function can be arbitrarily well-approximated by a network whose parameters are appropriately chosen real numbers.
1 code implementation • 1 Mar 2021 • Wojciech Czaja, Ilya Kavalerov, Weilin Li
We explore feature space geometries induced by the 3-D Fourier scattering transform and deep neural network with extended attribute profiles on four standard hyperspectral images.
no code implementations • 1 Mar 2021 • Wojciech Czaja, Weilin Li, Yiran Li, Mike Pekala
Inspired by the Hardy-Littlewood maximal function, we propose a novel pooling strategy which is called maxfun pooling.
no code implementations • 11 Oct 2020 • Weilin Li, Kui Ren, Donsub Rim
The range characterization is obtained by first showing that the ADRT is a bijection between images supported on infinite half-strips, then identifying the linear subspaces that stay finitely supported under the inversion formula.
2 code implementations • 17 Jun 2019 • Ilya Kavalerov, Weilin Li, Wojciech Czaja, Rama Chellappa
Recent developments in machine learning and signal processing have resulted in many new techniques that are able to effectively capture the intrinsic yet complex properties of hyperspectral imagery.