Sparse Wavelet Networks. Sadri, A., Celebi, M., Rahnavard, N., & Viswanath, S. IEEE Signal Processing Letters, 2020.
doi  abstract   bibtex   
A wavelet network (WN) is a feed-forward neural network that uses wavelets as activation functions for the neurons in its hidden layer. By predetermining the wavelet positions and dilations, the WN can turn into a linear regression model. The common approach for the construction of these WN families is to use least-squares type algorithms. In this letter, we propose a novel approach by formulating a WN as a sparse linear regression problem, which we call a sparse wavelet network (SWN). In this WN, the problem of calculating the unknown inner parameters of the network becomes that of finding the sparse solution of an under-determined system of linear equations. Our sparse solution algorithm is a non-convex sparse relaxation approach inspired by smoothed L0 (SL0), a distinguished sparse recovery algorithm. The proposed SWN can be applied as a tool for the prediction and identification of dynamical systems.
@article{
 title = {Sparse Wavelet Networks},
 type = {article},
 year = {2020},
 keywords = {Wavelet network,non-convex regularization,sparse representation,system identification},
 volume = {27},
 id = {a179b9b6-3f1b-3438-9b0d-eaf61bff30b5},
 created = {2023-10-25T08:56:39.135Z},
 file_attached = {false},
 profile_id = {eaba325f-653b-3ee2-b960-0abd5146933e},
 last_modified = {2023-10-25T08:56:39.135Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {false},
 hidden = {false},
 private_publication = {true},
 abstract = {A wavelet network (WN) is a feed-forward neural network that uses wavelets as activation functions for the neurons in its hidden layer. By predetermining the wavelet positions and dilations, the WN can turn into a linear regression model. The common approach for the construction of these WN families is to use least-squares type algorithms. In this letter, we propose a novel approach by formulating a WN as a sparse linear regression problem, which we call a sparse wavelet network (SWN). In this WN, the problem of calculating the unknown inner parameters of the network becomes that of finding the sparse solution of an under-determined system of linear equations. Our sparse solution algorithm is a non-convex sparse relaxation approach inspired by smoothed L0 (SL0), a distinguished sparse recovery algorithm. The proposed SWN can be applied as a tool for the prediction and identification of dynamical systems.},
 bibtype = {article},
 author = {Sadri, A.R. and Celebi, M.E. and Rahnavard, N. and Viswanath, S.E.},
 doi = {10.1109/LSP.2019.2959219},
 journal = {IEEE Signal Processing Letters}
}

Downloads: 0