Extended hamming neural network for non binary pattern recognition

Juan Carlos Sanchez Garcia; Mariko Nakano Miyatake; Hector Perez Meana; Luis Nino de Rivera y Oyarzabal

Extended hamming neural network for non binary pattern recognition

Juan Carlos Sanchez Garcia, Mariko Nakano Miyatake, Hector Perez Meana, Luis Nino de Rivera y Oyarzabal

Research output: Contribution to conference › Paper › peer-review

Abstract

An extended Hamming neural network structure is proposed for recognition of non binary input patterns. Proposed structure is based on splitting the input pattern into N binary input patterns, where N is the number of bits used for representing each pixel of the original input pattern. Subsequently each binary pattern is processed for a Hamming neural network. Finally the outputs of each binary neural network are used to identify the non binary input pattern. Simulation results show that proposed structures performs fairly well for input patterns with 40% of their pixels distorted.

Original language	English
Pages	607-609
Number of pages	3
State	Published - 1994
Externally published	Yes
Event	Proceedings of the 37th Midwest Symposium on Circuits and Systems. Part 2 (of 2) - Lafayette, LA, USA Duration: 3 Aug 1994 → 5 Aug 1994

Conference

Conference	Proceedings of the 37th Midwest Symposium on Circuits and Systems. Part 2 (of 2)
City	Lafayette, LA, USA
Period	3/08/94 → 5/08/94

Cite this

@conference{5cf7d33eb8c245558182ea4dd808bba1,

title = "Extended hamming neural network for non binary pattern recognition",

abstract = "An extended Hamming neural network structure is proposed for recognition of non binary input patterns. Proposed structure is based on splitting the input pattern into N binary input patterns, where N is the number of bits used for representing each pixel of the original input pattern. Subsequently each binary pattern is processed for a Hamming neural network. Finally the outputs of each binary neural network are used to identify the non binary input pattern. Simulation results show that proposed structures performs fairly well for input patterns with 40% of their pixels distorted.",

author = "{Sanchez Garcia}, {Juan Carlos} and Miyatake, {Mariko Nakano} and Meana, {Hector Perez} and {de Rivera y Oyarzabal}, {Luis Nino}",

year = "1994",

language = "Ingl{\'e}s",

pages = "607--609",

note = "Proceedings of the 37th Midwest Symposium on Circuits and Systems. Part 2 (of 2) ; Conference date: 03-08-1994 Through 05-08-1994",

}

TY - CONF

T1 - Extended hamming neural network for non binary pattern recognition

AU - Sanchez Garcia, Juan Carlos

AU - Miyatake, Mariko Nakano

AU - Meana, Hector Perez

AU - de Rivera y Oyarzabal, Luis Nino

PY - 1994

Y1 - 1994

N2 - An extended Hamming neural network structure is proposed for recognition of non binary input patterns. Proposed structure is based on splitting the input pattern into N binary input patterns, where N is the number of bits used for representing each pixel of the original input pattern. Subsequently each binary pattern is processed for a Hamming neural network. Finally the outputs of each binary neural network are used to identify the non binary input pattern. Simulation results show that proposed structures performs fairly well for input patterns with 40% of their pixels distorted.

AB - An extended Hamming neural network structure is proposed for recognition of non binary input patterns. Proposed structure is based on splitting the input pattern into N binary input patterns, where N is the number of bits used for representing each pixel of the original input pattern. Subsequently each binary pattern is processed for a Hamming neural network. Finally the outputs of each binary neural network are used to identify the non binary input pattern. Simulation results show that proposed structures performs fairly well for input patterns with 40% of their pixels distorted.

UR - http://www.scopus.com/inward/record.url?scp=0028758223&partnerID=8YFLogxK

M3 - Artículo

AN - SCOPUS:0028758223

SP - 607

EP - 609

T2 - Proceedings of the 37th Midwest Symposium on Circuits and Systems. Part 2 (of 2)

Y2 - 3 August 1994 through 5 August 1994

ER -

Extended hamming neural network for non binary pattern recognition

Abstract

Conference

Other files and links

Fingerprint

Cite this