The problem of path planning is studied for t he case for a mobile robot moving in a known environment. An aggressive algorith m using a description of the obstacles based on a neural network is proposed. Th e algorit...The problem of path planning is studied for t he case for a mobile robot moving in a known environment. An aggressive algorith m using a description of the obstacles based on a neural network is proposed. Th e algorithm allows to construct an optimal path which is piecewise linear with c hanging directions of the obstacles and the calculation speed for the proposed a lgorithm is comparatively fast. Simulation results and an application to a car_l ike robot 'Khepera' show the effectiveness of the proposed algorithm.展开更多
Instead of existing methods,a recurrent neural network is conceived to deal with three stages of portfolio management.Mainly,a deterministic annealing neural network is proposed for the approach to portfolio problem,w...Instead of existing methods,a recurrent neural network is conceived to deal with three stages of portfolio management.Mainly,a deterministic annealing neural network is proposed for the approach to portfolio problem,which is a kind of quadratic programming.Finally,through a real example,we verify that the neural network model proposed in this paper is a good tool to solve the portfolio problem.展开更多
Since there were few chaotic neural networks applicable to the global optimization, in this paper, we propose a new neural network model ? chaotic parameters disturbance annealing (CPDA) network, which is superior to ...Since there were few chaotic neural networks applicable to the global optimization, in this paper, we propose a new neural network model ? chaotic parameters disturbance annealing (CPDA) network, which is superior to other existing neural networks, genetic algorithms, and simulated annealing algorithms in global optimization. In the present CPDA network, we add some chaotic parameters in the energy function, which make the Hopfield neural network escape from the attraction of a local minimal solution and with the parameter annealing, our model will converge to the global optimal solutions quickly and steadily. The converge ability and other characters are also analyzed in this paper. The benchmark examples show the present CPDA neural network's merits in nonlinear global optimization.展开更多
文摘The problem of path planning is studied for t he case for a mobile robot moving in a known environment. An aggressive algorith m using a description of the obstacles based on a neural network is proposed. Th e algorithm allows to construct an optimal path which is piecewise linear with c hanging directions of the obstacles and the calculation speed for the proposed a lgorithm is comparatively fast. Simulation results and an application to a car_l ike robot 'Khepera' show the effectiveness of the proposed algorithm.
基金Supported by the National Science Foundatin of China (No.79670 0 64)
文摘Instead of existing methods,a recurrent neural network is conceived to deal with three stages of portfolio management.Mainly,a deterministic annealing neural network is proposed for the approach to portfolio problem,which is a kind of quadratic programming.Finally,through a real example,we verify that the neural network model proposed in this paper is a good tool to solve the portfolio problem.
文摘Since there were few chaotic neural networks applicable to the global optimization, in this paper, we propose a new neural network model ? chaotic parameters disturbance annealing (CPDA) network, which is superior to other existing neural networks, genetic algorithms, and simulated annealing algorithms in global optimization. In the present CPDA network, we add some chaotic parameters in the energy function, which make the Hopfield neural network escape from the attraction of a local minimal solution and with the parameter annealing, our model will converge to the global optimal solutions quickly and steadily. The converge ability and other characters are also analyzed in this paper. The benchmark examples show the present CPDA neural network's merits in nonlinear global optimization.
