Abstract
It is considered a basic approach for hybrid neuron network creation. As an example, the counter propagation neural network is analyzed. It is effectively used for image processing. Two modes of this neuron network functioning are considered. They are: accreditation and interpolation. Interpolation mode permits to reveal more complex features and can supply more precise results. Based on this analysis it is developed a new hybrid structure that includes Kohonnen neural network and perceptron. It is proposed a learning algorithm of this hybrid neuron network.
Highlights
The problem of combining different types of neural structures in a single architecture, which leads to properties that they do not have separately is often discussed [1] – [6]. The example of such combining is counter propagation network. It is developed a system architecture based on the counter-distribution network, but instead of the Grossberg network, it is taken a single-layer perceptron
SYNTHESIS OF HYBRID NETWORK To determine the problem of structural synthesis of a hybrid neural network based on Kohonen and the perceptron, it is necessary to analyze three mechanisms necessary for the operation of this network
When connecting a network with a perceptron is the best the result of the hybrid network will be in interpolation mode
Summary
The counter propagation neural network is analyzed. It is effectively used for image processing. Two modes of this neuron network functioning are considered. Interpolation mode permits to reveal more complex features and can supply more precise results. Based on this analysis it is developed a new hybrid structure that includes Kohonnen neural network and perceptron. It is proposed a learning algorithm of this hybrid neuron network
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
