Variable Step-Size Nonholonomic Natural Gradient Algorithm Based on Optimal Selective Function

By introducing the nonholonomic constraints, the nonholonomic natural gradient algorithm is effective to overcome the shortcomings of traditional natural gradient algorithm. Namely, when the source signal amplitude changes rapidly over time or is equal to zero in a certain period of time, it can still work well. In addition, selecting the different estimate function in different stage can get the balance between convergence speed and steady-state performance. Thus, this paper combines the nonholonomic natural gradient with the optimal selective function to obtain a new algorithm. Furthermore, a variable step-size which is based on the gradient of cost function is also applied to the proposed algorithm to balance the contradiction between convergence speed and the error in steady state. Computer simulation results show that the performance of approved algorithm is superior to the usual algorithm, which can greatly accelerate the convergence rate and maintain good steady-state error at the same time.