This paper describes the implementation of a genetic algorithm to evolve the population of weight matrices for storing and recalling the patterns in a Hopfield type neural network model. In the Hopfield type neural ne...
详细信息
This paper describes the implementation of a genetic algorithm to evolve the population of weight matrices for storing and recalling the patterns in a Hopfield type neural network model. In the Hopfield type neural network of associative memory, the appropriate arrangement of synaptic weights provides an associative function in the network. The energy function associated with the stable state of this model represents the appropriate storage of the input patterns. The aim is to obtain the optimal weight matrix for efficient recall of any prototype input pattern. For this, we explore the population generation technique (mutation and elitism), crossover and the fitness evaluation function for generating the new population of the weight matrices. This process continues until the selection of the last weight matrix or matrices has been performed. The experiments incorporate a neural network trained with multiple numbers of patterns using the Hebbian learning rule. In most cases, the recalling of patterns using a genetic algorithm seems to give better results than the conventional recalling with the Hebbian rule. The simulated results suggest that the genetic algorithm is the better searching technique for recalling noisy prototype input patterns. (C) 2010 Elsevier Ltd. All rights reserved.
A RBF neural networkcontrol system optimized by Particle Swarm optimization is proposed. The control system was constructed by two RBF neural network, one was used as identifier and the other was used as controller. ...
A RBF neural networkcontrol system optimized by Particle Swarm optimization is proposed. The control system was constructed by two RBF neural network, one was used as identifier and the other was used as controller. The system parameters were optimized by PSO, RBF neural network identified the nonlinear controlled object, the obtained Jacobian information used into RBF controller. Simulation results shows that the system optimized by PSO can get the ideal results of the control to the nonlinear objects, the system has good adaptive capacity and robustness.
The proceedings contain 140 papers. The topics discussed include: Cartesian impedance control on five-finger dexterous robot hand DLR-HIT II with flexible joint;changeable grasping force unit for under-actuated grippe...
ISBN:
(纸本)3642165834
The proceedings contain 140 papers. The topics discussed include: Cartesian impedance control on five-finger dexterous robot hand DLR-HIT II with flexible joint;changeable grasping force unit for under-actuated gripper with self-adaptive grasping;efficient grasp planning with reachability analysis;development of an anthropomorphic prosthetic hand for man-machine interaction;a novel coupled and self-adaptive under-actuated grasping mode and the COSA-DTS hand;empirical copula driven hand motion recognition via surface electromyography based templates;a continuous control scheme for multifunctional robotic arm with surface EMG signal;a behavior-based path planning for autonomous vehicle;an uncertainty approach for fixture layout optimization using Monte Carlo method;the small-world network model of mixed production line;improved inertial pose estimation algorithms for on-site hydraulic turbine blade repairing robot;and pursuit evasion in dynamic environments with visibility constraints.
The proceedings contain 140 papers. The topics discussed include: Cartesian impedance control on five-finger dexterous robot hand DLR-HIT II with flexible joint;changeable grasping force unit for under-actuated grippe...
ISBN:
(纸本)3642165869
The proceedings contain 140 papers. The topics discussed include: Cartesian impedance control on five-finger dexterous robot hand DLR-HIT II with flexible joint;changeable grasping force unit for under-actuated gripper with self-adaptive grasping;efficient grasp planning with reachability analysis;development of an anthropomorphic prosthetic hand for man-machine interaction;a novel coupled and self-adaptive under-actuated grasping mode and the COSA-DTS hand;empirical copula driven hand motion recognition via surface electromyography based templates;a continuous control scheme for multifunctional robotic arm with surface EMG signal;a behavior-based path planning for autonomous vehicle;an uncertainty approach for fixture layout optimization using Monte Carlo method;the small-world network model of mixed production line;improved inertial pose estimation algorithms for on-site hydraulic turbine blade repairing robot;and pursuit evasion in dynamic environments with visibility constraints.
In this paper, we extend our previous optimization investigation on a single cell (IEEE Transactions on Wireless Communications, vol. 8, no. 2, pp. 1038-1044, 2009) to a whole network with multiple cells and further c...
详细信息
H.264/AVC the latest international video coding standard achieves higher compression efficiency than previous video coding standards. However, this performance gain comes at the cost of an increased computational comp...
详细信息
The traditional PID control is difficult in the nonlinear, delay, time-varying conditions and have a disturbance characteristics in supercritical main steam temperature control system to achieve satisfactory control e...
详细信息
ISBN:
(纸本)9781424465392;9781424465422
The traditional PID control is difficult in the nonlinear, delay, time-varying conditions and have a disturbance characteristics in supercritical main steam temperature control system to achieve satisfactory control effect. This paper presents a neural network predictive control method using multi-step prediction, rolling optimization and feedback correction control strategy, achieved good control results. Taking the supercritical main steam temperature as the research object, MATLAB simulation results show that, in various of the main steam temperature condition neural network dynamic model, both are well predict the dynamic characteristic, and achieved better performances than traditional PID's.
Nowadays, the performance of p2p applications is limited by the network-oblivious peering and the scarcity of network resources, which leads to lots of wastes of networking resources and times. Hence, a light-weight a...
详细信息
Nowadays, the performance of p2p applications is limited by the network-oblivious peering and the scarcity of network resources, which leads to lots of wastes of networking resources and times. Hence, a light-weight architecture called p4p was proposed, it can control each p2p peers intelligently and achieve the goal of service optimization by reducing multi-download data transmission. In this paper, the performance of p4p is compared with several other optimization methods, the advantage of p4p framework is shown clearly in our evaluation results.
The Tactical Internet (TI) is a new and highly maneuverable network, so traditional network management (NM) methods can't solve its NM well, new methods needs to be explored. In this paper, the modeling of TI NM w...
详细信息
The Tactical Internet (TI) is a new and highly maneuverable network, so traditional network management (NM) methods can't solve its NM well, new methods needs to be explored. In this paper, the modeling of TI NM was researched at first, the action model, function model and organizing model were established and they settled the framework of TI NM. Secondly, the frequency planning of TI NM was researched, an algorithm based on maximum chromaticity coloring and simulated annealing was proposed, it improved the utilization ratio of frequency resource. Thirdly, the dynamic control of TI NM was researched, a new method based on control variable was proposed, it solved the dynamic control relationship establishing between the controller and controllee. The paper's work has been applied and verified in practical use.
暂无评论