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
{"_id":"uFtqd2BEFyyhwBpDg","bibbaseid":"sadri-celebi-rahnavard-viswanath-sparsewaveletnetworks-2020","authorIDs":["4Bygm8ju5EJL5ymrQ","6QhxQnZANogYLvQK3","95yz33vzsQF4xkftF","9XZAWfqroLnhv8Yvi","FNZqkqoLDpk7PuWdD","MFZedjHxD2knXtEDJ","QcPeEw2JciXtbZFYv","h2B3dsR3oRk42DaEg","ikoetnssERNBFB49Z","kEjtqmTXpJD7idBiM","mKXojsM3x8movswn3","mTxR5EmKaPZT4FPRw","wqGyw5WWC92w63FBr","zmtHQr2MyDkT4KaPS","zy5Yt2FBfMrjEQLRW"],"author_short":["Sadri, A.","Celebi, M.","Rahnavard, N.","Viswanath, S."],"bibdata":{"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","bibtex":"@article{\n title = {Sparse Wavelet Networks},\n type = {article},\n year = {2020},\n keywords = {Wavelet network,non-convex regularization,sparse representation,system identification},\n volume = {27},\n id = {a179b9b6-3f1b-3438-9b0d-eaf61bff30b5},\n created = {2023-10-25T08:56:39.135Z},\n file_attached = {false},\n profile_id = {eaba325f-653b-3ee2-b960-0abd5146933e},\n last_modified = {2023-10-25T08:56:39.135Z},\n read = {false},\n starred = {false},\n authored = {true},\n confirmed = {false},\n hidden = {false},\n private_publication = {true},\n 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.},\n bibtype = {article},\n author = {Sadri, A.R. and Celebi, M.E. and Rahnavard, N. and Viswanath, S.E.},\n doi = {10.1109/LSP.2019.2959219},\n journal = {IEEE Signal Processing Letters}\n}","author_short":["Sadri, A.","Celebi, M.","Rahnavard, N.","Viswanath, S."],"biburl":"https://bibbase.org/service/mendeley/eaba325f-653b-3ee2-b960-0abd5146933e","bibbaseid":"sadri-celebi-rahnavard-viswanath-sparsewaveletnetworks-2020","role":"author","urls":{},"keyword":["Wavelet network","non-convex regularization","sparse representation","system identification"],"metadata":{"authorlinks":{"viswanath, s":"https://bibbase.org/service/mendeley/eaba325f-653b-3ee2-b960-0abd5146933e","viswanath, s":"https://bibbase.org/show?msg=embed&bib=https://dblp.org/pid/75/5518.bib"}},"downloads":0},"bibtype":"article","creationDate":"2020-04-20T04:32:18.576Z","downloads":0,"keywords":["wavelet network","non-convex regularization","sparse representation","system identification"],"search_terms":["sparse","wavelet","networks","sadri","celebi","rahnavard","viswanath"],"title":"Sparse Wavelet Networks","year":2020,"biburl":"https://bibbase.org/service/mendeley/eaba325f-653b-3ee2-b960-0abd5146933e","dataSources":["EqsrWP7MGiqJ6MAPy","ya2CyA73rpZseyrZ8","MFTLffJ4nzQec8k8n","2252seNhipfTmjEBQ"]}