Hybrid Neural Network Model Based on Multi-layer Perceptron and Adaptive Resonance Theory

Gavrilov, A. V.; Lee, Young-Koo; Lee, Sungyoung

doi:10.1007/11759966_104

Cited by 6 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The perceptron is a linear classification model that works by classifying an input feature vector [28] into two classes (+1 or −1) by means of a linear discriminant function, specifically the linear discriminant function has the following mathematical Eq. (1):…”

Section: Statistical Classification Modelsmentioning

confidence: 99%

A study on the phenomenon of anaphoric correction in college students’ English conversation

Zhang¹

2022

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

English education for college students is a major instructional programme with significant developmental importance; yet, its conversations are also crucial. Reflexivity in conversational repair refers to the tendency of speakers to go back to the beginning of the repairing component rather than to implement the repair directly after the wrong word. In order to help listeners solve the connection problem, speakers use different back-referencing strategies. In this study, we used a quantitative and qualitative approach to explore the patterns and strategies of finger-back repair in Chinese college students’ English conversations and to compare their similarities and differences with native speakers in the use of finger-back onset words. The study found that the proportion of self-repetition was the highest among college students, reaching about 75%, and the proportion of reorganisation and insertion strategies was very small, about 23%, which reflected the characteristics of college students’ ability in linguistic information processing and online processing; moreover, there were significant differences between them and native speakers in the use of reflexive priming words. This paper borrows from the attention theory of cognitive psychology to explain the results and to point out the implications of this study for the teaching of spoken English in college.

show abstract

Section: Statistical Classification Modelsmentioning

confidence: 99%

A study on the phenomenon of anaphoric correction in college students’ English conversation

Zhang¹

2022

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

show abstract

“…O seguinte procedimento consistiu em aplicar a rotina de modificação da rede até que não houvesse Finalmente e comoé apresentado na tabela (1) á ultima rede achada, onde a rotina programada não consegue aumentar o raio dos neurônios sem invadir outras classes,é a quinta rede, a figura (7.e) apresenta a topologia e o tamanho da classe, já na figura (9)é observado a diferencia entre o tamanho da classe representado pelos neurônios iniciais (figura (6)) e o tamanho das classes da rede final. Neste exemplo se procura observar o comportamento do algoritmo utilizando dados que podem ser divididos em diversos tipos de dados, um tipo de aplicação pode ser a identificação de objetos para robótica móvel [8], neste exemplo em O procedimento de redução ou simplificação de redes neurais de raio variável tipo ART, resultou ser mais sofisticado do previsto inicialmente pelos autores deste documento, a intervenção de diversas variáveis que influencia o sucesso da redução da rede, aumentou a dificuldade do trabalho, mas gerou uma grande satisfação ao observar os resultados finais do algoritmo proposto.…”

Section: Exemplo De Reduçãounclassified

Redução De Número De Neurônios De Raio Variável Em Redes Tipo Art.

Calôba¹,

Dutra²,

Orjuela³

et al. 2016

Anais Do 9. Congresso Brasileiro De Redes Neurais

View full text Add to dashboard Cite

Abstract-The neural network's relevance for clustering different kind of data has encouraged diverse works in order to optimize their implementation. Between the areas of research, exist ones that seek to reduce the number of neurons needed to define a specific class. In this work the authors present an algorithm that allows the reduction of number of neurons width variable radius in ART's networks, the procedure used is listed as semisupervised, but has features that allow its application in conjunction with not supervised techniques . Several tests were performed to assess the effectiveness of this method, two of the most important and informative examples are presented.Keywords-Art Network, Semi-supervised training, Not supervised reduction .Resumo-A importância das redes neurais para a clusterisação de diferentes tipos de dados tem impulso diversos trabalhos para conseguir técnicas que otimizem a aplicação das mesmas. Entre asáreas de pesquisa estão aquelas que procuram a redução do número de neurônios necessários para definir uma classe. Neste trabalho os autores apresentam um algoritmo que permite a redução de número de neurônios de raio variável numa rede tipo ART, o procedimento utilizadoé catalogado como semi-supervisionado, mas com características que permitem sua aplicação em conjunto com técnicas não supervisionadas. Diversos testes foram feitos avaliando a eficácia deste método, dois dos mais importantes e esclarecedores da técnica são apresentados .Keywords-Redes Art, Treinamento Semi-Supervisionado, Redução Não-Supervisionada. Introdução.A clusterização por meio de redes neuraisé uma técnica que tem demonstrado serútil em diversos tipos de aplicações, usando técnicas de treinamento supervisionado ou não supervisionada, mantendo sempre o objetivo geral de obter redes que possam identificar padrões semelhantes entre diversos dados O bloco 1 unido com o bloco 2, permite a criação de redes capazes de definir, depois de um treinamento ART, que neurônios representam uma determinada classe. Finalmente a união do bloco 1 com o bloco 3 permite criar a rede Counterpropagation onde os termos P n representam os padrões que representam cada neurônio.A variável denominada de Bias (B i ), permite-lhe a um neurônio i ter umaárea de cobertura maior o menor dependendo do seu valor, a relação do B i com o raio de cobertura do neurônio (r i ) está dada pela equação (1).Definido o B ié possível pensar em redes que tenham neurônios de diferentes raios de cobertura [7],

show abstract

“…For the first time the paradigm of MLP-ART2 model was proposed by us in [17], [18]. In that paper the idea was suggested and some previous experiments and problems were shown.…”

Section: Introductionmentioning

confidence: 99%

An Approach for Invariant Clustering and Recognition in Dynamic Environment

Gavrilov

Lee

Advances and Innovations in Systems, Computing Sciences and Software Engineering

Self Cite

View full text Add to dashboard Cite

-An approach for invariant clustering and recognition of objects (situation) in dynamic environment is proposed. This approach is based on the combination of clustering by using unsupervised neural network (in particular ART-2) and preprocessing of sensor information by using forward multilayer perceptron (MLP) with error back propagation (EBP) which supervised by clustering neural network. Using MLP with EBP allows to recognize a pattern with relatively small transformations (shift, rotation, scaling) as a known previous cluster and to reduce producing large number of clusters in dynamic environment, e.g. during movement of robot or recognition of novelty in security system.

show abstract

Hybrid Neural Network Model Based on Multi-layer Perceptron and Adaptive Resonance Theory

Cited by 6 publications

References 9 publications

A study on the phenomenon of anaphoric correction in college students’ English conversation

A study on the phenomenon of anaphoric correction in college students’ English conversation

Redução De Número De Neurônios De Raio Variável Em Redes Tipo Art.

An Approach for Invariant Clustering and Recognition in Dynamic Environment

Contact Info

Product

Resources

About