- All Journals
- Al-Qadisiyah University
- Basrah University
- Kirkuk University
- Mosul University
- The Iraqi Borad for Medical Specialization
- University of Anbar
- University of Technology
- Al Mustafa University
- Al-Zahraa University for Women
- Alnoor University
- Kunooz University
- Misan University
- Ninevah University
- Tikrit University
- University of Al-Hamdaniya
- University of Kerbala
ON FEED FORWARD NEURAL NETWORK WITH RIDGE BASIS FUNCTION | ||
| journal of al-qadisiyah for pure science(quarterly) | ||
| Article 1, Volume 7, Issue 4, 2007, Pages 214-220 PDF (0 K) | ||
| Authors | ||
| ; Q.H. Eqhaar | ||
| Abstract | ||
| In this paper, we show the degree of approximation by a single hidden layer feed forward model with n units in the hidden layer is bounded below by the degree of approximation by a linear combination of n ridge functions. We prove that there exists an analytic, strictly monotone, sigmoidal activation function for which this lower bound is essentially attained. Also we extend the Kolmogorov’s existence theorem to be apply at any compact set, (i.e., closed and bounded set) also we prove that a FFNN with one hidden layer can uniformly approximate any continuous function of several variable, f(x1, x2, …, xn), which is defined in compact set to any required accuracy. | ||
|
Statistics Article View: 118 PDF Download: 65 |
||