A Novel Strategy for Improving the Counter Propagation Artificial Neural Networks in Classification Tasks

Counter-Propagation-Artificial-Neural-Networks (C P-ANNs) have been applied in several domains due to their learning and classification abilities. Regardless of strength, the CP-ANNs still some limitations pattern recognition tasks when they encounter ambiguities during process, which leads inaccurate Kohonen-Self-Organizing-Map (K-SOM). This problem has an impact on performance CP-ANNs. Therefore, this paper proposes a novel strategy improve by Gram-Schmidt algorithm (GSHM) as pre-processing step original data without changing architecture. Three datasets examples from various domains, such correlation, crop, fertilizer, were employed for experimental validation. To obtain results, we relied two simulations. The first simulation uses CP-ANNs, are inputted into network any prior pre-processing. second MCP-ANNs, pre-processed through GSHM block. Experiment results show that proposed MCP-ANNs recognize all patterns with accuracy 100% versus 62.5% Correlation Dataset. Furthermore, reduce execution time training parameter values Thus, approach based significantly improves