BCR-Net: a neural network based on the nonstandard wavelet form

10/20/2018
by   Yuwei Fan, et al.
0

This paper proposes a novel neural network architecture inspired by the nonstandard form proposed by Beylkin, Coifman, and Rokhlin in [Communications on Pure and Applied Mathematics, 44(2), 141-183]. The nonstandard form is a highly effective wavelet-based compression scheme for linear integral operators. In this work, we first represent the matrix-vector product algorithm of the nonstandard form as a linear neural network where every scale of the multiresolution computation is carried out by a locally connected linear sub-network. In order to address nonlinear problems, we propose an extension, called BCR-Net, by replacing each linear sub-network with a deeper and more powerful nonlinear one. Numerical results demonstrate the efficiency of the new architecture by approximating nonlinear maps that arise in homogenization theory and stochastic computation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/13/2017

Neural Network Based Nonlinear Weighted Finite Automata

Weighted finite automata (WFA) can expressively model functions defined ...
research
12/25/2022

FMM-Net: neural network architecture based on the Fast Multipole Method

In this paper, we propose a new neural network architecture based on the...
research
04/20/2020

Towards deep neural network compression via learnable wavelet transforms

Wavelets are well known for data compression, yet have rarely been appli...
research
03/31/2022

A comparative study between linear and nonlinear speech prediction

This paper is focused on nonlinear prediction coding, which consists on ...
research
10/26/2017

PDE-Net: Learning PDEs from Data

In this paper, we present an initial attempt to learn evolution PDEs fro...
research
11/09/2022

LiCo-Net: Linearized Convolution Network for Hardware-efficient Keyword Spotting

This paper proposes a hardware-efficient architecture, Linearized Convol...
research
03/03/2022

Nonlinear predictive models computation in ADPCM schemes

Recently several papers have been published on nonlinear prediction appl...

Please sign up or login with your details

Forgot password? Click here to reset