“…The learning algorithm of the LPN is summarized in the following [7]: However, the distinctive feature of learn- ing in the LPN is not that all variable parameters of the network will be modified but rather that only the variable parameter related to the route in which the token has propagated is modified.…”
Section: Learning Algorithmmentioning
confidence: 99%
“…The effectiveness of the LPN has been clarified by applying it to a pattern recognition problem [6,7] and a system identification problem [8]. The effectiveness of the LPN has been clarified by applying it to a pattern recognition problem [6,7] and a system identification problem [8].…”
“…The learning algorithm of the LPN is summarized in the following [7]: However, the distinctive feature of learn- ing in the LPN is not that all variable parameters of the network will be modified but rather that only the variable parameter related to the route in which the token has propagated is modified.…”
Section: Learning Algorithmmentioning
confidence: 99%
“…The effectiveness of the LPN has been clarified by applying it to a pattern recognition problem [6,7] and a system identification problem [8]. The effectiveness of the LPN has been clarified by applying it to a pattern recognition problem [6,7] and a system identification problem [8].…”
“…However, the distinctive feature of learn- ing in the LPN is not that all variable parameters of the network will be modified but rather that only the variable parameter related to the route in which the token has propagated is modified. The learning algorithm of the LPN is summarized in the following [7]:…”
Section: Learning Algorithmmentioning
confidence: 99%
“…x Crane stand system In Eqs. (7) to (9), letting hT 1 , t x, hT 2 , t x , hT 3 , t T, hT 4 , t T , hT 5 , t l, hT 6 , t l , and discretizing with a sampling time 'T, the equations become those shown below.…”
Section: Controlled Systemmentioning
confidence: 99%
“…For the purpose of realizing, by learning, this function distribution inside a network, the authors proposed a learning Petri network (LPN) which unites a Petri net based on a distribution route and a neural network (NN) having a learning function. The effectiveness of the LPN has been clarified by applying it to a pattern recognition problem [6,7] and a system identification problem [8].…”
According to the recent knowledge of brain sience, it is suggested that there exists functions distribu tion in the brain, which means that different neurons are activated depending on which sort of sensory information the brain receives. We have already developed a learning network with functions distribution which is called Learn ing Petri Network(L.P.N.) and have also shown that this network could learn nonlinear and discontinuous mappings which Neural Network(N.N.) can not. In this paper, a more realistic application which has dynamic characteristics is studied. From simulation results of a nonlinear crane control system using L.P.N. controller, it is clarified that the control performance of L.P.N. controller is superior to that of N.N. controller.
According to recent knowledge of brain science it is suggested that there exists functions distribution, which means that specific parts exist in the brain for realizing specific functions. This paper introduces a new brain-like model called Learning Petri Network (LPN) that has the capability of functions distribution and learning. The idea is to use Petri net to realize the functions distribution and to incorporate the learning and representing ability of neural network into the Petri net. The obtained LPN can be used in the same way as a neural network to model and control dynamic systems, while it is distinctive to a neural network in that it has the capability of functions distribution. An application of the LPN to nonlinear crane control systems is discussed. It is shown via numerical simulations that the proposed LPN controller has superior performance to the commonly-used neural network one.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.