New neural networks based on taylor series and their research

Xiaoyun Chen; Qiang Ma; Talal Alkharobi

doi:10.1109/ICCSIT.2009.5234726

New neural networks based on taylor series and their research

Xiaoyun Chen^*, Qiang Ma, Talal Alkharobi

^*Corresponding author for this work

Department of Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Scopus citations

Abstract

This paper is Mining in the essence of neural networks,and constructing 4 types of neural networks: (1) to construct a neural network based on Taylor series; (2) to construct a Taylor component neural network which brings in a Radial Basis Function neuron as a prefix; (3) to construct a Fourier component neural network.Because of the relationships between these functions,the Taylor component NN and the Fourier component NN can be called Gauss series NN equivalently; (4) to construct a Gauss series Clustering neural network and to prove its equivalence with RBF NN in a limit situation.The development of new types of neural Networks is playing an important role either to promote deepening study of neural networks theory or to provide new methods for applications.

Original language	English
Title of host publication	Proceedings - 2009 2nd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2009
Pages	291-294
Number of pages	4
DOIs	https://doi.org/10.1109/ICCSIT.2009.5234726
State	Published - 2009

Publication series

Name	Proceedings - 2009 2nd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2009

Keywords

Fourier component neural network
Gauss series clustering neural network
Prediction
Stock price
Taylor component neural network
Taylor series neural network

ASJC Scopus subject areas

Computer Science Applications
Information Systems
Software

Access to Document

10.1109/ICCSIT.2009.5234726

Cite this

Chen, X., Ma, Q., & Alkharobi, T. (2009). New neural networks based on taylor series and their research. In Proceedings - 2009 2nd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2009 (pp. 291-294). [5234726] (Proceedings - 2009 2nd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2009). https://doi.org/10.1109/ICCSIT.2009.5234726

@inproceedings{635ecc1cb31443d3b6bf6e01b811b263,

title = "New neural networks based on taylor series and their research",

abstract = "This paper is Mining in the essence of neural networks,and constructing 4 types of neural networks: (1) to construct a neural network based on Taylor series; (2) to construct a Taylor component neural network which brings in a Radial Basis Function neuron as a prefix; (3) to construct a Fourier component neural network.Because of the relationships between these functions,the Taylor component NN and the Fourier component NN can be called Gauss series NN equivalently; (4) to construct a Gauss series Clustering neural network and to prove its equivalence with RBF NN in a limit situation.The development of new types of neural Networks is playing an important role either to promote deepening study of neural networks theory or to provide new methods for applications.",

keywords = "Fourier component neural network, Gauss series clustering neural network, Prediction, Stock price, Taylor component neural network, Taylor series neural network",

author = "Xiaoyun Chen and Qiang Ma and Talal Alkharobi",

year = "2009",

doi = "10.1109/ICCSIT.2009.5234726",

language = "English",

isbn = "9781424445196",

series = "Proceedings - 2009 2nd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2009",

pages = "291--294",

booktitle = "Proceedings - 2009 2nd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2009",

}

Chen, X, Ma, Q & Alkharobi, T 2009, New neural networks based on taylor series and their research. in Proceedings - 2009 2nd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2009., 5234726, Proceedings - 2009 2nd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2009, pp. 291-294. https://doi.org/10.1109/ICCSIT.2009.5234726

New neural networks based on taylor series and their research. / Chen, Xiaoyun; Ma, Qiang; Alkharobi, Talal.
Proceedings - 2009 2nd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2009. 2009. p. 291-294 5234726 (Proceedings - 2009 2nd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2009).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - New neural networks based on taylor series and their research

AU - Chen, Xiaoyun

AU - Ma, Qiang

AU - Alkharobi, Talal

PY - 2009

Y1 - 2009

N2 - This paper is Mining in the essence of neural networks,and constructing 4 types of neural networks: (1) to construct a neural network based on Taylor series; (2) to construct a Taylor component neural network which brings in a Radial Basis Function neuron as a prefix; (3) to construct a Fourier component neural network.Because of the relationships between these functions,the Taylor component NN and the Fourier component NN can be called Gauss series NN equivalently; (4) to construct a Gauss series Clustering neural network and to prove its equivalence with RBF NN in a limit situation.The development of new types of neural Networks is playing an important role either to promote deepening study of neural networks theory or to provide new methods for applications.

AB - This paper is Mining in the essence of neural networks,and constructing 4 types of neural networks: (1) to construct a neural network based on Taylor series; (2) to construct a Taylor component neural network which brings in a Radial Basis Function neuron as a prefix; (3) to construct a Fourier component neural network.Because of the relationships between these functions,the Taylor component NN and the Fourier component NN can be called Gauss series NN equivalently; (4) to construct a Gauss series Clustering neural network and to prove its equivalence with RBF NN in a limit situation.The development of new types of neural Networks is playing an important role either to promote deepening study of neural networks theory or to provide new methods for applications.

KW - Fourier component neural network

KW - Gauss series clustering neural network

KW - Prediction

KW - Stock price

KW - Taylor component neural network

KW - Taylor series neural network

UR - http://www.scopus.com/inward/record.url?scp=70449089086&partnerID=8YFLogxK

U2 - 10.1109/ICCSIT.2009.5234726

DO - 10.1109/ICCSIT.2009.5234726

M3 - Conference contribution

AN - SCOPUS:70449089086

SN - 9781424445196

T3 - Proceedings - 2009 2nd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2009

SP - 291

EP - 294

BT - Proceedings - 2009 2nd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2009

ER -

Chen X, Ma Q, Alkharobi T. New neural networks based on taylor series and their research. In Proceedings - 2009 2nd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2009. 2009. p. 291-294. 5234726. (Proceedings - 2009 2nd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2009). doi: 10.1109/ICCSIT.2009.5234726

New neural networks based on taylor series and their research

Abstract

Publication series

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this