Abstract
A hierarchical hybrid neural network comprising simple neural networks provided significantly higher accuracy in data retrieval that single neural network architectures. Both approaches were applied to information retrieval from large databases using textual retrieval keys where either the retrieval key or the data in the database are noisy. The results were improved by using different network training methods for highly correlated and less correlated data. The combination of self-organizing and supervised learning neural networks solved this problem, providing a retrieval accuracy of 93% when presented with noisy data, providing a fast training time, and allowing the solution to be scaled up

This publication has 3 references indexed in Scilit: