Contradiction Resolution between Self and Outer Evaluation for Supervised Multi-Layered Neural Networks
Journal Title: International Journal of Advanced Research in Artificial Intelligence(IJARAI) - Year 2013, Vol 2, Issue 7
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
- EP ID EP98678
- DOI -
- Views 146
- Downloads 0
A Novel Control-Navigation System- Based Adaptive Optimal Controller & EKF Localization of DDMR
This paper presents a newly developed approach for Differential Drive Mobile Robot (DDMR). The main goal is to provide a high dynamic system response in the joint space level, the low level control, as well as to e...
Blocking Black Area Method for Speech Segmentation
Speech segmentation is an important sub problem of automatic speech recognition. This research is concerned with the development of a continuous speech segmentation system using Bangla Language. This paper presents...
Brain Computer Interface Boulevard of Smarter Thoughts
The Brain Computer Interface is a major breakthrough for the technical industry, medical world, military and the society on a whole. It is concerned with the control of devices around us such as computing gears & eve...
Method for Psychological Status Monitoring with Line of Sight Vector Changes (Human Eye Movements) Detected with Wearing Glass
Method for psychological status monitoring with line of sight vector changes (human eye movement) detected with wearing glass is proposed. Succored eye movement should be an indicator of humans’ psychological statu...
Analysis of Gumbel Model for Software Reliability Using Bayesian Paradigm
In this paper, we have illustrated the suitability of Gumbel Model for software reliability data. The model parameters are estimated using likelihood based inferential procedure: classical as well as Bayesian. The quasi...