Rice Yield prediction - a comparison between Enchanced Back Propagation Learning Algorithms
Back Propagation algorithm(BP) has been popularly used to solve various problems, however it is shrouded with the problems of low convergence and instability. In recent years, improvements have been attempted to overcome the discrepancies aforementioned. In this study, we examine the performance of...
保存先:
主要な著者: | , , , , |
---|---|
フォーマット: | 論文 |
言語: | English |
出版事項: |
Universiti Malaysia Perlis
2009
|
主題: | |
オンライン・アクセス: | http://dspace.unimap.edu.my/xmlui/handle/123456789/6982 |
タグ: |
タグ追加
タグなし, このレコードへの初めてのタグを付けませんか!
|
要約: | Back Propagation algorithm(BP) has been popularly used to solve various problems, however it is shrouded with the problems of low convergence and instability. In recent years, improvements have been attempted to overcome the discrepancies aforementioned. In this study, we examine the performance of four enhanced BP algorithms to predict rice yield in MAD A plantation area in Kedah, Malaysia. A midst the four algorithms explored, Conjugate Gradient Descent exhibits the best performance. |
---|