engleski

Neuronska mreže bez Bias neurona u skrivenom sloju

In this paper the nonlinear dynamic discrete-time neuron model, the so-called Dynamic Elementary Processor (DEP) is proposed. This dynamic neuron disposes of local memory, in that it has dynamic states. To accelerate the convergence of proposed extended dynamic error-back propagation learning algorithm, the adaptive neuron activation is applied. Instead of most popular unipolar and bipolar Sigmoidal neuron activation functions, the Gauss activation function with adaptive parameters is proposed. Based on the DEP neuron with adaptive activation function in hidden layer, and without Bias neuron for hidden layer, a Dynamic Multi Layer Neural Network is proposed and used for the identification of discrete-time nonlinear dynamic system.

dynamic neural network; adaptive activation function; bias neuron; identification

nije evidentirano