Record Details

STUDI ANALISA PELATIHAN JARINGAN SYARAF TIRUAN DENGAN DAN TANPA ALGORITMA GENETIKA

Jurnal Informatika

View Archive Info
 
 
Field Value
 
Title STUDI ANALISA PELATIHAN JARINGAN SYARAF TIRUAN DENGAN DAN TANPA ALGORITMA GENETIKA
 
Creator Noertjahyana, Agustinus; Faculty of Industrial Engineering, Petra Christian University
Yulia, Yulia; Faculty of Industrial Engineering, Petra Christian University
 
Subject neural nerwork, genetic algorithm, ortificial intelligence
 
Description Neural network as an information processor system which has some similarities with human brain, is lately used to solve general problems. Neural network has several characteristics based on : architecture, learning algorithm, and activation function. Genetic algorithm is a method to get an optimum function using genetic operations which is done to each individual in a population that is often called as chromosome. This way, to get a more optimum function is by colliding neural network and genetic algorithm. That is by doing a bias conversion and the weight to the neural network into a kind of individual form of genetic algorithm and the other way arround. Thus, a conclusion can be drawn about neural network learning method with or without genetic algorithm.


Abstract in Bahasa Indonesia :

Neural network sebagai suatu sistem pengolah informasi yang mempunyai kemiripan dengan jaringan otak manusia, belakangan ini sering digunakan untuk menyelesaikan suatu permasalahan. Neural network memiliki beberapa karakteristik yang ditentukan oleh : arsitektur, algoritma pelatihan serta fungsi aktivasi. Algoritma genetika adalah suatu metode untuk mendapatkan suatu fungsi yang optimal dengan menggunakan operasi-operasi genetika yang dilakukan pada tiap-tiap individu yang terdapat dalam suatu populasi yang seringkali disebut sebagai kromosom. Dalam hal ini untuk mendapatkan kemungkinan suatu fungsi bisa lebih optimal adalah dengan menggabungkan antara neural network dengan algoritma genetika. Adapun caranya adalah dengan melakukan proses konversi bias dan bobot pada neural network ke dalam bentuk individu pada algoritma genetika dan demikian sebaliknya. Sehingga nantinya bisa didapatkan suatu kesimpulan antara metode pelatihan neural network dengan dan tanpa menggunakan algoritma genetika.

Kata kunci: jaringan saraf tiruan, olgaritma genetika, kecerdasan buatan..
 
Publisher Institute of Research and Community Outreach - Petra Christian University
 
Date 2004-06-18
 
Type info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
 
Format application/pdf
 
Identifier http://jurnalinformatika.petra.ac.id/index.php/inf/article/view/15812
10.9744/informatika.3.1.pp. 12-16
 
Source Jurnal Informatika; Vol 3, No 1 (2002): MAY 2002; pp. 12-16
 
Language eng
 
Relation http://jurnalinformatika.petra.ac.id/index.php/inf/article/view/15812/15804
 
Rights Authors who publish with this journal agree to the following terms:Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.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 acknowledgement of its initial publication in this journal.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 (See The Effect of Open Access).