TY  - JOUR
T1  - Approximation by Regular Neural Networks in Terms of Dunkl Transform
AU - Bhaya, Eman AU - Al-sammak, Omar 
JO  - Research Journal of Applied Sciences
VL  - 11
IS  - 10
SP  - 933
EP  - 941
PY  - 2016
DA  - 2001/08/19
SN  - 1815-932x
DO  - rjasci.2016.933.941
UR  - https://makhillpublications.co/view-article.php?doi=rjasci.2016.933.941
KW  - Neural network approximation
KW  -saturation problem
KW  -spaces
KW  -direct inequality
AB  - Dunkl operator here we introduce a modified version of and use it to prove a theorem shows that functionals and rth order modulus of smoothness in K-theorem shows thatare equivalent. We use this equivalence to introduce p&lt;1 spaces for L<sub>p</sub> (K) essential degree of approximation using regular neural networks p and how a multivariate function in spaces for can be approximated using a p&lt;1 spaces for L<sub>p</sub> (K) multivariate p function in forward regular neural network. So, we can have the essential approximation using regular FFN. P&lt;1 spaces for L<sub>p</sub> (K) ability of a multivariate function in spaces for using regular FFN.
ER  -