抄録
In this paper, a complex multi-layer neural network that is conducted its training by using complex back propagation algorithm is applied to solve inverse kinematics a robot manipulator and to control an inverted pendulum. Computational experiments are carried out to investigate the characteristics of the complex back propagation algorithm. Experimental results of the inverse kinematics show that the performance of complex neural network is a little advantage than a real number neural network in local minimum problem. Experimental results of the inverted pendulum also show that the complex neural network learns faster than the real number neural network and achieves higher success rate in generalization problems.
