Echo state networks are a relatively new type of recurrent neural networks that have shown great potentials for solving nonlinear,\r\ntemporal problems. The basic idea is to transform the low dimensional temporal input into a higher dimensional state,\r\nand then train the output connection weights to make the system output the target information. Because only the output weights\r\nare altered, training is typically quick and computationally efficient compared to training of other recurrent neural networks. This\r\npaper investigates using an echo state network to learn the inverse kinematics model of a robot simulator with feedback-errorlearning.\r\nIn this scheme teacher forcing is not perfect, and joint constraints on the simulator makes the feedback error inaccurate.\r\nA novel trainingmethod which is less influenced by the noise in the training data is proposed and compared to the traditional ESN\r\ntraining method.
Loading....