Skripsi
PENGARUH JUMLAH HIDDEN LAYER DIDALAM ARSITEKTUR BACKPROPAGATION PADA ALGORITMA NEURO FUZZY TERHADAP PENDIAGNOSAAN BREAST CANCER WISCONSIN
The Backpropagation algorithm has a weakness in processing data directly from the experience of experts without knowing the tendency to enter the target. Fuzzy Logic is the right choice in overcoming this, because the function of fuzzy logic is to create a degree of membership where the value of a higher degree of membership in a target can indicate that the data will enter the target. The effect of the number of hidden layers on the results of the training test can be known by looking at the error value. The smaller the error value, the better the accuracy will be. So the results of the study in comparing the effect of the number of hidden layers in the backpropagation architecture on the Neuro Fuzzy algorithm for the diagnosis of Breast Cancer Wisconsin, resulted in different accuracy, where the application of 2 hidden layers resulted in a better accuracy rate of 93.66% while the application of 1 hidden layer resulted in accuracy. by 91.22%.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2107002672 | T50927 | T509272021 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available