Metode pembangkitan bobot untuk jaringan syaraf tiruan dengan algoritma fungsi Boolean = Weights Generators Method for Neural Network with Boolean Function Algorithm
According to Hadjar's experimental results, ANN with Boolean function algorithm offered many advantages than complicated ANN such as Neocognitron. Although it was successful because of its simplicity and efficiency. Some of weights generators generate binary weights using Boolean function and t...
| Main Author: | |
|---|---|
| Format: | Article |
| Published: |
[Yogyakarta] : Universitas Gadjah Mada
2004
|
| Subjects: |
| _version_ | 1797017643941625856 |
|---|---|
| author | Perpustakaan UGM, i-lib |
| author_facet | Perpustakaan UGM, i-lib |
| author_sort | Perpustakaan UGM, i-lib |
| collection | UGM |
| description | According to Hadjar's experimental results, ANN with Boolean function algorithm offered many advantages than complicated ANN such as Neocognitron. Although it was successful because of its simplicity and efficiency. Some of weights generators generate binary weights using Boolean function and the other using non-binary weights such as Perceptron.
Because of lack of information was contained in Hadjar's experimental results, lead me to compare some binary weights generators using AND, OR, and XOR (common operators in Boolean function) and also non-binary weights generators that were modified from classical ANN, Perceptron.
After some experiments, I can conclude that the best binary weights generator is using OR operator. But the best weights generator of all is 'non-binary weights generator 1' that have already modified from Perceptron. AND maybe the worst one, but it can be considered if images are homogeneous.
Key words : Boolean function algorithm, Weights generator |
| first_indexed | 2024-03-05T22:52:27Z |
| format | Article |
| id | oai:generic.eprints.org:17666 |
| institution | Universiti Gadjah Mada |
| last_indexed | 2024-03-05T22:52:27Z |
| publishDate | 2004 |
| publisher | [Yogyakarta] : Universitas Gadjah Mada |
| record_format | dspace |
| spelling | oai:generic.eprints.org:176662014-06-18T00:28:29Z https://repository.ugm.ac.id/17666/ Metode pembangkitan bobot untuk jaringan syaraf tiruan dengan algoritma fungsi Boolean = Weights Generators Method for Neural Network with Boolean Function Algorithm Perpustakaan UGM, i-lib Jurnal i-lib UGM According to Hadjar's experimental results, ANN with Boolean function algorithm offered many advantages than complicated ANN such as Neocognitron. Although it was successful because of its simplicity and efficiency. Some of weights generators generate binary weights using Boolean function and the other using non-binary weights such as Perceptron. Because of lack of information was contained in Hadjar's experimental results, lead me to compare some binary weights generators using AND, OR, and XOR (common operators in Boolean function) and also non-binary weights generators that were modified from classical ANN, Perceptron. After some experiments, I can conclude that the best binary weights generator is using OR operator. But the best weights generator of all is 'non-binary weights generator 1' that have already modified from Perceptron. AND maybe the worst one, but it can be considered if images are homogeneous. Key words : Boolean function algorithm, Weights generator [Yogyakarta] : Universitas Gadjah Mada 2004 Article NonPeerReviewed Perpustakaan UGM, i-lib (2004) Metode pembangkitan bobot untuk jaringan syaraf tiruan dengan algoritma fungsi Boolean = Weights Generators Method for Neural Network with Boolean Function Algorithm. Jurnal i-lib UGM. http://i-lib.ugm.ac.id/jurnal/download.php?dataId=427 |
| spellingShingle | Jurnal i-lib UGM Perpustakaan UGM, i-lib Metode pembangkitan bobot untuk jaringan syaraf tiruan dengan algoritma fungsi Boolean = Weights Generators Method for Neural Network with Boolean Function Algorithm |
| title | Metode pembangkitan bobot untuk jaringan syaraf tiruan dengan algoritma fungsi Boolean = Weights Generators Method for Neural Network with Boolean Function Algorithm |
| title_full | Metode pembangkitan bobot untuk jaringan syaraf tiruan dengan algoritma fungsi Boolean = Weights Generators Method for Neural Network with Boolean Function Algorithm |
| title_fullStr | Metode pembangkitan bobot untuk jaringan syaraf tiruan dengan algoritma fungsi Boolean = Weights Generators Method for Neural Network with Boolean Function Algorithm |
| title_full_unstemmed | Metode pembangkitan bobot untuk jaringan syaraf tiruan dengan algoritma fungsi Boolean = Weights Generators Method for Neural Network with Boolean Function Algorithm |
| title_short | Metode pembangkitan bobot untuk jaringan syaraf tiruan dengan algoritma fungsi Boolean = Weights Generators Method for Neural Network with Boolean Function Algorithm |
| title_sort | metode pembangkitan bobot untuk jaringan syaraf tiruan dengan algoritma fungsi boolean weights generators method for neural network with boolean function algorithm |
| topic | Jurnal i-lib UGM |
| work_keys_str_mv | AT perpustakaanugmilib metodepembangkitanbobotuntukjaringansyaraftiruandenganalgoritmafungsibooleanweightsgeneratorsmethodforneuralnetworkwithbooleanfunctionalgorithm |