no code implementations • 28 Dec 2020 • Te-Chun Wang, Yuan-Chung Sheu
Motivated by the general matrix deviation inequality for i. i. d ensemble Gaussian matrix, we study its universality property.
Probability
no code implementations • 21 Nov 2020 • Gi-Ren Liu, Yuan-Chung Sheu, Hau-Tieng Wu
On the whole, NAST is a transform that comprises a sequence of ``neural processing units'', each of which applies a high pass filter to the input from the previous layer followed by a composition with a nonlinear function as the output to the next neuron.