際際滷shows by User: PanagiotisPetsagoura / http://www.slideshare.net/images/logo.gif 際際滷shows by User: PanagiotisPetsagoura / Sun, 26 Jul 2015 20:24:43 GMT 際際滷Share feed for 際際滷shows by User: PanagiotisPetsagoura Control of a nonlinear non affine discrete system using neural networks and online training with reinforcement learning methods /slideshow/diploma-50945776/50945776 diploma-150726202443-lva1-app6891
My diploma thesis: Control of a nonlinear non affine discrete system using neural networks and online training with reinforcement learning methods Online control of a nonlinear non affine discrete system, using RBF neural networks Online adaptation of the centers of networks, with changing the number of the nodes The reinforcement learning is implemented with one neural network, which is the critic network, while one more neural network is used to produce the manipulated variable.]]>
My diploma thesis: Control of a nonlinear non affine discrete system using neural networks and online training with reinforcement learning methods Online control of a nonlinear non affine discrete system, using RBF neural networks Online adaptation of the centers of networks, with changing the number of the nodes The reinforcement learning is implemented with one neural network, which is the critic network, while one more neural network is used to produce the manipulated variable.]]> Sun, 26 Jul 2015 20:24:43 GMT /slideshow/diploma-50945776/50945776 PanagiotisPetsagoura@slideshare.net(PanagiotisPetsagoura) Control of a nonlinear non affine discrete system using neural networks and online training with reinforcement learning methods PanagiotisPetsagoura My diploma thesis: Control of a nonlinear non affine discrete system using neural networks and online training with reinforcement learning methods Online control of a nonlinear non affine discrete system, using RBF neural networks Online adaptation of the centers of networks, with changing the number of the nodes The reinforcement learning is implemented with one neural network, which is the critic network, while one more neural network is used to produce the manipulated variable. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/diploma-150726202443-lva1-app6891-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> My diploma thesis: Control of a nonlinear non affine discrete system using neural networks and online training with reinforcement learning methods Online control of a nonlinear non affine discrete system, using RBF neural networks Online adaptation of the centers of networks, with changing the number of the nodes The reinforcement learning is implemented with one neural network, which is the critic network, while one more neural network is used to produce the manipulated variable.
Control of a nonlinear non affine discrete system using neural networks and online training with reinforcement learning methods from Panagiotis Petsagkourakis
]]> 254 4 https://cdn.slidesharecdn.com/ss_thumbnails/diploma-150726202443-lva1-app6891-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 https://cdn.slidesharecdn.com/profile-photo-PanagiotisPetsagoura-48x48.jpg?cb=1525771707