ملخص
In this paper, an algorithm for the design of functional link single layer neural networks using N binary inputs is described. The resulting connection weights are pure integer numbers. These integer weights facilitate faster learning by the neural network due to binary operations rather than algebraic multiplications. Comparison between various learning algorithms, mainly backpropagation with the delta rule, and the functional link approach is demonstrated via several recognition applications. It is illustrated that the functional link approach, due to enhancing input patterns, produces a robust algorithm for linearly non-separable classification problems in terms of processing speed and convergence. Furthermore, implementation of the neural network can be accomplished using the vast availability of off-the-shelf components and VLSI techniques.
| اللغة الأصلية | English |
|---|---|
| الصفحات (من إلى) | 66-88 |
| عدد الصفحات | 23 |
| دورية | Kuwait Journal of Science and Engineering |
| مستوى الصوت | 26 |
| رقم الإصدار | 1 |
| حالة النشر | Published - 1999 |
بصمة
أدرس بدقة موضوعات البحث “Learning with integer weighted functional link preceptron'. فهما يشكلان معًا بصمة فريدة.قم بذكر هذا
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver