<![CDATA[Rapid population growth rate that can influence government policies on various aspects of life. It is necessary for the proper way to reduce the rate of population growth and create a safer contraceptive choice. Windowed momentum is a technique to improve the performance in backpropagation learning. But to ensure the accuracy of the momentum needed windowed performance computing methods such as neural networks to solve problems with the accuracy of data and not linear. Neural Network Optimization tested weeks to produce the best accuracy rate, applying Neural Network-based Backward Elimination aims to raise the accuracy produced by Neural Network. Experiments were performed to obtain the optimal architecture and generate increased accuracy. The results of the research is a confusion matrix to prove the accuracy of Neural Network before Backward Elimination is optimized by 54.64% and 57.03% after optimize. This proves estimate windowed momentum trials using neural network-based method Backward Elimination more accurate than the individual methods of neural network.]]>
Copyrights © 2015
