The number of new students at AMIK-STIKOM Tunas Bangsa Pematangsiantar greatly influences the improvement and development of available facilities both academically and non-academically. In this study, the author will conduct a prediction process on the object of new students which aims to determine the number of new students at AMIK-STIKOM Tunas Bangsa Pematangsiantar by applying the backpropagation learning algorithm. Backpropagation is one method on artificial neural networks that is quite reliable in solving problems including predictions. The study uses six (6) architectural models: 3-12-1, 3-13-1, 3-14-1, 3-15-1, 3-16-1, 3-18-1, from the six architectural models obtained the best architecture with 75% accuracy, epoch 96 iterations in 1 second, namely architecture 3-16-1. The best architecture obtained is expected to be used as an illustration by the academic AMIK-STIKOM Tunas Bangsa in anticipating the development and increasing number of new students.
An End-User Platform for FPGA-Based Design and Rapid Prototyping of Feedforward Artificial Neural Networks With On-Chip Backpropagation Learning
