Contradiction Resolution between Self and Outer Evaluation for Supervised Multi-Layered Neural Networks

Abstract

In this paper, we propose a new type of informationtheoretic method. We suppose that a neuron should be evaluated from different points of view to precisely discern its properties. In this paper, we restrict ourselves to two types of evaluation methods for neurons, namely, self and outer-evaluation. A neuron fires only as a result of evaluating itself, while the neuron can fire as a result of evaluation by all surrounding neurons. Selfand outer-evaluation should be equivalent to each other. When contradiction between two types of evaluation exists, the contradiction should be as small as possible. Contradiction between self- and outer-evaluations is realized in terms of the Kullback- Leibler divergence between two types of neurons. Contradiction between self- and outer-evaluation can be resolved by decreasing the contradiction ratio between the two types of evaluation in terms of KL divergence. This method is expected to extract the main features in input patterns, if those are shared by two types of evaluation. We applied the method to two data sets, namely, the logistic and dollar-yen exchange rate data. In both problems, experimental results showed that visualization performance could be improved, leading to clearer class structure for both problems. In addition, when visualization was improved, generalization performance did not necessarily degrade, showing the possibility of networks with better visualization and prediction performance.

Authors and Affiliations

Ryotaro Kamimura

Keywords

Related Articles

The Need for a New Data Processing Interface for Digital Forensic Examination

Digital forensic science provides tools, techniques and scientifically proven methods that can be used to acquire and analyze digital evidence. There is a need for law enforcement agencies, government and private organis...

 Blurring and Deblurring Digital Images Using the Dihedral Group

 A new method of blurring and deblurring digital images is presented. The approach is based on using new filters generating from average filter and H-filters using the action of the dihedral group. These filters are...

 Using Unlabeled Data to Improve Inductive Models by Incorporating Transductive Models

 This paper shows how to use labeled and unlabeled data to improve inductive models with the help of transductivemodels.We proposed a solution for the self-training scenario. Self- training is an effective semi-supe...

Improved Scatter Search Using Cuckoo Search

The Scatter Search (SS) is a deterministic strategy that has been applied successfully to some combinatorial and continuous optimization problems. Cuckoo Search (CS) is heuristic search algorithm which is inspired by the...

 Cogntive Consistency Analysis in Adaptive Bio-Metric Authentication System Design

 Cognitive consistency analysis aims to continuously monitor one's perception equilibrium towards successful accomplishment of cognitive task. Opposite to cognitive flexibility analysis – cognitive consistency analy...

Download PDF file
  • EP ID EP98678
  • DOI -
  • Views 160
  • Downloads 0

How To Cite

Ryotaro Kamimura (2013). Contradiction Resolution between Self and Outer Evaluation for Supervised Multi-Layered Neural Networks. International Journal of Advanced Research in Artificial Intelligence(IJARAI), 2(7), 29-38. https://europub.co.uk/articles/-A-98678