In this paper we discuss the learning convergence of the cerebellar model articulation controller (CMAC) in cyclic learning. We prove the following results. First, if the training samples are noiseless, the training a...In this paper we discuss the learning convergence of the cerebellar model articulation controller (CMAC) in cyclic learning. We prove the following results. First, if the training samples are noiseless, the training algorithm converges if and only if the learning rate is chosen from (0, 2). Second, when the training samples have noises, the learning algorithm will converge with a probability of one if the learning rate is dynandcally decreased. Third, in the case with noises, with a small but fixed learning rate ε.the mean square error of the weight sequences generated by the CMAC learning algorithm will be bounded by O(ε). Some simulation experlinents are carried out totest these results.展开更多
In this paper, we propose a behaviorbased path planner that can self learn in anunknown environment. A situated learning algorithm is designed which allows therobot to learn to coordinate several concurrent behaviors ...In this paper, we propose a behaviorbased path planner that can self learn in anunknown environment. A situated learning algorithm is designed which allows therobot to learn to coordinate several concurrent behaviors and improve its performanceby interacting with the environmellt. Behaviors are implemented using CMAC neuralnetworks. A simulation environment is set up and some simulation experiments arecarried out to rest our learning algorithm.展开更多
文摘In this paper we discuss the learning convergence of the cerebellar model articulation controller (CMAC) in cyclic learning. We prove the following results. First, if the training samples are noiseless, the training algorithm converges if and only if the learning rate is chosen from (0, 2). Second, when the training samples have noises, the learning algorithm will converge with a probability of one if the learning rate is dynandcally decreased. Third, in the case with noises, with a small but fixed learning rate ε.the mean square error of the weight sequences generated by the CMAC learning algorithm will be bounded by O(ε). Some simulation experlinents are carried out totest these results.
文摘In this paper, we propose a behaviorbased path planner that can self learn in anunknown environment. A situated learning algorithm is designed which allows therobot to learn to coordinate several concurrent behaviors and improve its performanceby interacting with the environmellt. Behaviors are implemented using CMAC neuralnetworks. A simulation environment is set up and some simulation experiments arecarried out to rest our learning algorithm.
