A learning automaton approach to trajectory learning and control system design using dynamic recurrent neural networks

摘要

This thesis presents a method for the training of dynamic, recurrent neural networks to generate continuous-time trajectories. In the past, most methods for this type of training were based on gradient descent methods and were deterministic. The method presented here is stochastic in nature. The problem of local minima is addressed by adding the enhancement of incremental learning to the learning automaton; i.e., small learning goals are used to train the neural network from its initialized state to its final parameters for the desired response. The method is applied to the learning of a benchmark continuous-time trajectory--the circle. Then the learning automaton approach is applied to stabilization and tracking problems for linear and nonlinear plant models, using either state or output feedback as needed.