Majority Algorithm: A Formation for Neural Networks with the Quantized Connection Weights

Cheol-Young PARK; Koji NAKAJIMA

Majority Algorithm: A Formation for Neural Networks with the Quantized Connection Weights

Cheol-Young PARK, Koji NAKAJIMA

Full Text Views

0

Cite this

Summary :

In this paper, we propose the majority algorithm to choose the connection weights for the neural networks with quantized connection weights of 1 and 0. We also obtained the layered network to solve the parity problem with the input of arbitrary number N through an application of this algorithm. The network can be expected to have the same ability of generalization as the network trained with learning rules. This is because it is possible to decide the connection weights, regardless of the size of the training set. One can decide connection weights without learning according to our case study. Thus, we expect that the proposed algorithm may be applied for a real-time processing.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E83-A No.6 pp.1059-1065

Publication Date: 2000/06/25

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Section of Papers Selected from 1999 International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC'99))

Category

Cite this

Copy

Cheol-Young PARK, Koji NAKAJIMA, "Majority Algorithm: A Formation for Neural Networks with the Quantized Connection Weights" in IEICE TRANSACTIONS on Fundamentals, vol. E83-A, no. 6, pp. 1059-1065, June 2000, doi: .
Abstract: In this paper, we propose the majority algorithm to choose the connection weights for the neural networks with quantized connection weights of 1 and 0. We also obtained the layered network to solve the parity problem with the input of arbitrary number N through an application of this algorithm. The network can be expected to have the same ability of generalization as the network trained with learning rules. This is because it is possible to decide the connection weights, regardless of the size of the training set. One can decide connection weights without learning according to our case study. Thus, we expect that the proposed algorithm may be applied for a real-time processing.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e83-a_6_1059/_p

Copy

@ARTICLE{e83-a_6_1059,
author={Cheol-Young PARK, Koji NAKAJIMA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Majority Algorithm: A Formation for Neural Networks with the Quantized Connection Weights},
year={2000},
volume={E83-A},
number={6},
pages={1059-1065},
abstract={In this paper, we propose the majority algorithm to choose the connection weights for the neural networks with quantized connection weights of 1 and 0. We also obtained the layered network to solve the parity problem with the input of arbitrary number N through an application of this algorithm. The network can be expected to have the same ability of generalization as the network trained with learning rules. This is because it is possible to decide the connection weights, regardless of the size of the training set. One can decide connection weights without learning according to our case study. Thus, we expect that the proposed algorithm may be applied for a real-time processing.},
keywords={},
doi={},
ISSN={},
month={June},}

Copy

TY - JOUR
TI - Majority Algorithm: A Formation for Neural Networks with the Quantized Connection Weights
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1059
EP - 1065
AU - Cheol-Young PARK
AU - Koji NAKAJIMA
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E83-A
IS - 6
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - June 2000
AB - In this paper, we propose the majority algorithm to choose the connection weights for the neural networks with quantized connection weights of 1 and 0. We also obtained the layered network to solve the parity problem with the input of arbitrary number N through an application of this algorithm. The network can be expected to have the same ability of generalization as the network trained with learning rules. This is because it is possible to decide the connection weights, regardless of the size of the training set. One can decide connection weights without learning according to our case study. Thus, we expect that the proposed algorithm may be applied for a real-time processing.
ER -