Abear Mohamed Ezz Eldin Kamel <br/><br/>
Enhancing the performance of neural learning algorithms used in independent component analysis /  
 تحسين الأداء لخوارزمات التعلم العصبى المستخدمة فى تحليل المركبات المستقلة 
Abear Mohamed Ezz Eldin Kamel ; Supervised Ibrahim Farag , Amr Goneid 
 - Cairo :   Abear Mohamed Ezz Eldin Kamel ,   2010 
 - 168 Leaves :   charts ;   30cm 
<br/><br/>Thesis (Ph.D.) - Cairo University - Faculty of Computers and Information Science - Department of Computer Science 
<br/><br/> Recently there has been an increasing interest in statistical models for learning data representations. A very popular method for this task is independent component analysis. The ICA methodology was initially proposed to solve the blind source separation (BSS) problem i.e. given only mixtures of a set of underlying sources, the task is to separate the mixed signals and retrieve the original sources 
<br/><br/>
<br/><br/><label>Subjects--Index Terms: </label>Computer Science Independent component Neural learning algorithms