BulDML at Institute of Mathematics and Informatics >
International Journal ITA >
2003 >
Volume 10 Number 2 >

Please use this identifier to cite or link to this item:

Title: Intellect Sensing of Neural Network that Trained to Classify Complex Signals
Authors: Reznik, A.
Galinskaya, A.
Keywords: Neural Networks
Complex Signals
Issue Date: 2003
Publisher: Institute of Information Theories and Applications FOI ITHEA
Abstract: An experimental comparison of information features used by neural network is performed. The sensing method was used. Suboptimal classifier agreeable to the gaussian model of the training data was used as a probe. Neural nets with architectures of perceptron and feedforward net with one hidden layer were used. The experiments were carried out with spatial ultrasonic data, which are used for car’s passenger safety system neural controller learning. In this paper we show that a neural network doesn’t fully make use of gaussian components, which are first two moment coefficients of probability distribution. On the contrary, the network can find more complicated regularities inside data vectors and thus shows better results than suboptimal classifier. The parallel connection of suboptimal classifier improves work of modular neural network whereas its connection to the network input improves the specialization effect during training.
ISSN: 1313-0463
Appears in Collections:Volume 10 Number 2

Files in This Item:

File Description SizeFormat
ijita10-2-p09.pdf166.59 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


Valid XHTML 1.0!   Creative Commons License