@inproceedings{
 title = {Learning and Approximation of Chaotic Time Series Using Wavelet-Networks},
 type = {inproceedings},
 year = {2005},
 pages = {182-188},
 volume = {2005},
 websites = {http://ieeexplore.ieee.org/document/1592217/},
 publisher = {IEEE},
 id = {f0c78b16-8af4-3042-b383-76ec1f5baa8a},
 created = {2020-07-06T21:18:24.859Z},
 file_attached = {false},
 profile_id = {940dd160-7d67-3a5f-b9f8-935da0571367},
 last_modified = {2021-10-23T16:55:26.722Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 abstract = {This paper presents a wavelet neural-network for learning and approximation of chaotic time series. Wavelet networks are a class of neural network that take advantage of good localization and approximation properties of multiresolution analysis. These networks use wavelets as activation functions in the hidden layer and a hierarchical method is used for learning. Comparisons are made between a wavelet network, tested with two different wavelets, and the typical feed-forward network trained with the back-propagation algorithm. The results reported in this paper show that wavelet networks have better approximation properties than back-propagation networks. © 2005 IEEE.},
 bibtype = {inproceedings},
 author = {Alarcon-Aquino, V. and Garcia-Trevino, E.S. and Rosas-Romero, R. and Ramirez-Cruz, J.F},
 doi = {10.1109/ENC.2005.27},
 booktitle = {Sixth Mexican International Conference on Computer Science (ENC'05)}
}

{"_id":"F5qjB7ezsL3LLYr8p","bibbaseid":"alarconaquino-garciatrevino-rosasromero-ramirezcruz-learningandapproximationofchaotictimeseriesusingwaveletnetworks-2005","downloads":0,"creationDate":"2018-11-17T18:27:25.865Z","title":"Learning and Approximation of Chaotic Time Series Using Wavelet-Networks","author_short":["Alarcon-Aquino, V.","Garcia-Trevino, E.","Rosas-Romero, R.","Ramirez-Cruz, J."],"year":2005,"bibtype":"inproceedings","biburl":"https://bibbase.org/service/mendeley/940dd160-7d67-3a5f-b9f8-935da0571367","bibdata":{"title":"Learning and Approximation of Chaotic Time Series Using Wavelet-Networks","type":"inproceedings","year":"2005","pages":"182-188","volume":"2005","websites":"http://ieeexplore.ieee.org/document/1592217/","publisher":"IEEE","id":"f0c78b16-8af4-3042-b383-76ec1f5baa8a","created":"2020-07-06T21:18:24.859Z","file_attached":false,"profile_id":"940dd160-7d67-3a5f-b9f8-935da0571367","last_modified":"2021-10-23T16:55:26.722Z","read":false,"starred":false,"authored":"true","confirmed":"true","hidden":false,"private_publication":false,"abstract":"This paper presents a wavelet neural-network for learning and approximation of chaotic time series. Wavelet networks are a class of neural network that take advantage of good localization and approximation properties of multiresolution analysis. These networks use wavelets as activation functions in the hidden layer and a hierarchical method is used for learning. Comparisons are made between a wavelet network, tested with two different wavelets, and the typical feed-forward network trained with the back-propagation algorithm. The results reported in this paper show that wavelet networks have better approximation properties than back-propagation networks. © 2005 IEEE.","bibtype":"inproceedings","author":"Alarcon-Aquino, V. and Garcia-Trevino, E.S. and Rosas-Romero, R. and Ramirez-Cruz, J.F","doi":"10.1109/ENC.2005.27","booktitle":"Sixth Mexican International Conference on Computer Science (ENC'05)","bibtex":"@inproceedings{\n title = {Learning and Approximation of Chaotic Time Series Using Wavelet-Networks},\n type = {inproceedings},\n year = {2005},\n pages = {182-188},\n volume = {2005},\n websites = {http://ieeexplore.ieee.org/document/1592217/},\n publisher = {IEEE},\n id = {f0c78b16-8af4-3042-b383-76ec1f5baa8a},\n created = {2020-07-06T21:18:24.859Z},\n file_attached = {false},\n profile_id = {940dd160-7d67-3a5f-b9f8-935da0571367},\n last_modified = {2021-10-23T16:55:26.722Z},\n read = {false},\n starred = {false},\n authored = {true},\n confirmed = {true},\n hidden = {false},\n private_publication = {false},\n abstract = {This paper presents a wavelet neural-network for learning and approximation of chaotic time series. Wavelet networks are a class of neural network that take advantage of good localization and approximation properties of multiresolution analysis. These networks use wavelets as activation functions in the hidden layer and a hierarchical method is used for learning. Comparisons are made between a wavelet network, tested with two different wavelets, and the typical feed-forward network trained with the back-propagation algorithm. The results reported in this paper show that wavelet networks have better approximation properties than back-propagation networks. © 2005 IEEE.},\n bibtype = {inproceedings},\n author = {Alarcon-Aquino, V. and Garcia-Trevino, E.S. and Rosas-Romero, R. and Ramirez-Cruz, J.F},\n doi = {10.1109/ENC.2005.27},\n booktitle = {Sixth Mexican International Conference on Computer Science (ENC'05)}\n}","author_short":["Alarcon-Aquino, V.","Garcia-Trevino, E.","Rosas-Romero, R.","Ramirez-Cruz, J."],"urls":{"Website":"http://ieeexplore.ieee.org/document/1592217/"},"biburl":"https://bibbase.org/service/mendeley/940dd160-7d67-3a5f-b9f8-935da0571367","bibbaseid":"alarconaquino-garciatrevino-rosasromero-ramirezcruz-learningandapproximationofchaotictimeseriesusingwaveletnetworks-2005","role":"author","metadata":{"authorlinks":{}},"downloads":0},"search_terms":["learning","approximation","chaotic","time","series","using","wavelet","networks","alarcon-aquino","garcia-trevino","rosas-romero","ramirez-cruz"],"keywords":[],"authorIDs":[],"dataSources":["uTykyhFv6T7J2dX6z","nyWSrx2yzJEsoe49A"]}