ANALISIS FUNGSI AKTIVASI JARINGAN SYARAF TIRUAN UNTUK MENDETEKSI KARAKTERISTIK BENTUK GELOMBANG SPEKTRA BABI DAN SAPI
Abstract
Artificial Neural Network (ANN) is beginning little by little to replace the task of an expert, even with the ANN can be a tool to replace a doctor. One of kind of ANN is backpropagation networks, this network can be used to training programs in order to be able to recognize whether it is pig or cow wave spectra. To determine the output in backpropagation training required suitable activation functions. Therefore, in this research will be compared to some of the activation function that can be used in training. Activation functions will be tested with the ratio test to determine the interval convergence. After tested with the ratio test it was found that the activation function tanh z was the best activation function to use the
backpropagation network training, because it has a weight range that can meet the methods used in the determination of weights. When tested with the data, the activation function tanh z is able to recognize correctly all trial datas. An expected in future research to examine the weight that makes the interval training to achieve fast convergence and the error bit.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish in UJMC (Unisda Journal of Mathematics and Computer Science) agree to the following terms:
1.Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
2.Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
3.Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.