Dynamic neural controller with somatic adaptation
D.H. Rao, Manas Gupta · 2002
A neural structure which is comprised of dynamic neural units with time-varying sigmoidal functions is proposed. The effect of sigmoidal gain on nonlinear dynamic systems is discussed. The learning and adaptive algorithm to determine the optimum sigmoidal gain, which results in selftuning of the neuron, is derived. The effectiveness of the proposed neural network is demonstrated through computer simulation studies.>