%0 Journal Article
	%A A. Mirzaaghazadeh and  H. Motameni and  M. Karshenas and  H. Nematzadeh
	%D 2007
	%J International Journal of Computer and Information Engineering
	%B World Academy of Science, Engineering and Technology
	%I Open Science Index 9, 2007
	%T Learning Flexible Neural Networks for Pattern Recognition
	%U https://publications.waset.org/pdf/16019
	%V 9
	%X Learning the gradient of neuron's activity function
like the weight of links causes a new specification which is
flexibility. In flexible neural networks because of supervising and
controlling the operation of neurons, all the burden of the learning is
not dedicated to the weight of links, therefore in each period of
learning of each neuron, in fact the gradient of their activity function,
cooperate in order to achieve the goal of learning thus the number of
learning will be decreased considerably.
Furthermore, learning neurons parameters immunes them against
changing in their inputs and factors which cause such changing.
Likewise initial selecting of weights, type of activity function,
selecting the initial gradient of activity function and selecting a fixed
amount which is multiplied by gradient of error to calculate the
weight changes and gradient of activity function, has a direct affect
in convergence of network for learning.
	%P 2676 - 2679