Divide & Loop to Classify Similar Data in a Neural Network

Abstract

In this paper, we develop a structure of a divide & loop neural network that can improve the classification performance in neural network learning with the similar kind of input data. To solve the classification errors by the similar input data at the learning of these neural network, it was used how to find the other input data of the data or detailed data scaling. However, in the above-described solution, the fundamental problem of similar input data has not been resolved. To solve this problem, we propose a method of the loop neural network by divide in accordance with the error learning data. In this paper, we provide a method that can improve it by classification rate by repeating a neural network in order to reduce the weight of similar data indirectly to solve the problem.



Author Information
Joohyung Song, Inha University, South Korea

Paper Information
Conference: ACSET2015
Stream: Technology and Society: Technologies

This paper is part of the ACSET2015 Conference Proceedings (View)
Full Paper
View / Download the full paper in a new tab/window

Posted by amp21