Fractional-order gradient descent learning of BP neural networks with Caputo derivative. Wang, J., Wen, Y., Gou, Y., Ye, Z., & Chen, H. Neural Networks, 89:19–30, May, 2017. ![Fractional-order gradient descent learning of BP neural networks with Caputo derivative [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Fractional calculus has been found to be a promising area of research for information processing and modeling of some physical systems. In this paper, we propose a fractional gradient descent method for the backpropagation (BP) training of neural networks. In particular, the Caputo derivative is employed to evaluate the fractional-order gradient of the error defined as the traditional quadratic energy function. The monotonicity and weak (strong) convergence of the proposed approach are proved in detail. Two simulations have been implemented to illustrate the performance of presented fractional-order BP algorithm on three small datasets and one large dataset. The numerical simulations effectively verify the theoretical observations of this paper as well.
@article{wang_fractional-order_2017,
title = {Fractional-order gradient descent learning of {BP} neural networks with {Caputo} derivative},
volume = {89},
issn = {08936080},
url = {https://linkinghub.elsevier.com/retrieve/pii/S0893608017300369},
doi = {10.1016/j.neunet.2017.02.007},
abstract = {Fractional calculus has been found to be a promising area of research for information processing and modeling of some physical systems. In this paper, we propose a fractional gradient descent method for the backpropagation (BP) training of neural networks. In particular, the Caputo derivative is employed to evaluate the fractional-order gradient of the error defined as the traditional quadratic energy function. The monotonicity and weak (strong) convergence of the proposed approach are proved in detail. Two simulations have been implemented to illustrate the performance of presented fractional-order BP algorithm on three small datasets and one large dataset. The numerical simulations effectively verify the theoretical observations of this paper as well.},
language = {en},
urldate = {2023-03-31},
journal = {Neural Networks},
author = {Wang, Jian and Wen, Yanqing and Gou, Yida and Ye, Zhenyun and Chen, Hua},
month = may,
year = {2017},
keywords = {/unread},
pages = {19--30},
}
Downloads: 0
{"_id":"dNvCmP5nPS9bmMGHr","bibbaseid":"wang-wen-gou-ye-chen-fractionalordergradientdescentlearningofbpneuralnetworkswithcaputoderivative-2017","author_short":["Wang, J.","Wen, Y.","Gou, Y.","Ye, Z.","Chen, H."],"bibdata":{"bibtype":"article","type":"article","title":"Fractional-order gradient descent learning of BP neural networks with Caputo derivative","volume":"89","issn":"08936080","url":"https://linkinghub.elsevier.com/retrieve/pii/S0893608017300369","doi":"10.1016/j.neunet.2017.02.007","abstract":"Fractional calculus has been found to be a promising area of research for information processing and modeling of some physical systems. In this paper, we propose a fractional gradient descent method for the backpropagation (BP) training of neural networks. In particular, the Caputo derivative is employed to evaluate the fractional-order gradient of the error defined as the traditional quadratic energy function. The monotonicity and weak (strong) convergence of the proposed approach are proved in detail. Two simulations have been implemented to illustrate the performance of presented fractional-order BP algorithm on three small datasets and one large dataset. The numerical simulations effectively verify the theoretical observations of this paper as well.","language":"en","urldate":"2023-03-31","journal":"Neural Networks","author":[{"propositions":[],"lastnames":["Wang"],"firstnames":["Jian"],"suffixes":[]},{"propositions":[],"lastnames":["Wen"],"firstnames":["Yanqing"],"suffixes":[]},{"propositions":[],"lastnames":["Gou"],"firstnames":["Yida"],"suffixes":[]},{"propositions":[],"lastnames":["Ye"],"firstnames":["Zhenyun"],"suffixes":[]},{"propositions":[],"lastnames":["Chen"],"firstnames":["Hua"],"suffixes":[]}],"month":"May","year":"2017","keywords":"/unread","pages":"19–30","bibtex":"@article{wang_fractional-order_2017,\n\ttitle = {Fractional-order gradient descent learning of {BP} neural networks with {Caputo} derivative},\n\tvolume = {89},\n\tissn = {08936080},\n\turl = {https://linkinghub.elsevier.com/retrieve/pii/S0893608017300369},\n\tdoi = {10.1016/j.neunet.2017.02.007},\n\tabstract = {Fractional calculus has been found to be a promising area of research for information processing and modeling of some physical systems. In this paper, we propose a fractional gradient descent method for the backpropagation (BP) training of neural networks. In particular, the Caputo derivative is employed to evaluate the fractional-order gradient of the error defined as the traditional quadratic energy function. The monotonicity and weak (strong) convergence of the proposed approach are proved in detail. Two simulations have been implemented to illustrate the performance of presented fractional-order BP algorithm on three small datasets and one large dataset. The numerical simulations effectively verify the theoretical observations of this paper as well.},\n\tlanguage = {en},\n\turldate = {2023-03-31},\n\tjournal = {Neural Networks},\n\tauthor = {Wang, Jian and Wen, Yanqing and Gou, Yida and Ye, Zhenyun and Chen, Hua},\n\tmonth = may,\n\tyear = {2017},\n\tkeywords = {/unread},\n\tpages = {19--30},\n}\n\n","author_short":["Wang, J.","Wen, Y.","Gou, Y.","Ye, Z.","Chen, H."],"key":"wang_fractional-order_2017","id":"wang_fractional-order_2017","bibbaseid":"wang-wen-gou-ye-chen-fractionalordergradientdescentlearningofbpneuralnetworkswithcaputoderivative-2017","role":"author","urls":{"Paper":"https://linkinghub.elsevier.com/retrieve/pii/S0893608017300369"},"keyword":["/unread"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/victorjhu","dataSources":["CmHEoydhafhbkXXt5"],"keywords":["/unread"],"search_terms":["fractional","order","gradient","descent","learning","neural","networks","caputo","derivative","wang","wen","gou","ye","chen"],"title":"Fractional-order gradient descent learning of BP neural networks with Caputo derivative","year":2017}