Title :
Interaction of individually and collectively treated neurons for explicit class structure in self-organizing maps
Author :
Kamimura, Ryotaro
Author_Institution :
IT Educ. Center, Hiratsuka, Japan
Abstract :
In this paper, we propose a new type of neural learning method where two types of neurons interact with other. The two types of neurons are individually and collectively treated neurons. Though there are many types of interaction between two neurons, we suppose for simplification that individually treated neurons should be similar to collectively treated neurons as much as possible. This model can be applied to the self-organizing maps whose performance can be enhanced by the introduction of interaction of neurons. Then, we applied the method to the breast tissue and protein classification problem of the machine learning database. The experimental results showed that much clearer class boundaries could be produced, though quantization and topographic errors were slightly higher than those by the conventional SOM.
Keywords :
biological tissues; biology computing; learning (artificial intelligence); pattern classification; proteins; self-organising feature maps; SOM; breast tissue classification problem; collectively treated neuron interaction; explicit class structure; individually treated neuron interaction; machine learning database; neural learning method; protein classification problem; quantization errors; self-organizing maps; topographic errors; Weight measurement;
Conference_Titel :
Neural Networks (IJCNN), The 2012 International Joint Conference on
Conference_Location :
Brisbane, QLD
Print_ISBN :
978-1-4673-1488-6
Electronic_ISBN :
2161-4393
DOI :
10.1109/IJCNN.2012.6252415