We construct a pattern recognition system by modeling the structure of the visual cortex. The complexities of the visual cortex can be simplified by understanding that the neurons of this region are distinguished by t...
详细信息
ISBN:
(纸本)9783540368397
We construct a pattern recognition system by modeling the structure of the visual cortex. The complexities of the visual cortex can be simplified by understanding that the neurons of this region are distinguished by the features of input image that each neuron detects. We propose a neural network(NN) model of the simple structure based on the function and structure of the visual cortex. Moreover, a lot of ideas of manufactured products with NN were proposed. One of issues for productization is uncertainty of the behavior of nonlinearity of NN. Accordingly, it is important to analyze the internal representation of NN. In this paper, we discuss the recognition and training mechanism of a NN model by use of alopex algorithm. alopex algorithm, which is an iterative and stochastic processing to minimize or maximize a cost function. processing to minimize or maximize a cost function. By this method, the receptive fields of the units in the output layer are obtained. We have proposed a four-layered feed-forward NN model for pattern recognition and analyzed the recognition mechanism as well as the performance of the model. We proposed a modified alopex algorithm and calculated the receptive fields of the output unit. In the case of simple training character set, the receptive field changes according to the values of initial weight vectors. If the initial values are large, NN uses small amounts of input values for the classification. In contrast, if the initial values are small, NN uses whole input image. Moreover, it was seen that as the complexity of the set of training patterns increased the receptive field of the output unit changed. Smaller initial values of weight vector have advantage to get the more features. alopex algorithm is an effective method to find the characteristics of images.
alopex is a heuristic and optimum algorithm. A self-adaptive and variable step length alopex algorithm was raised to exceed local optimal solution and to approximate global optimal solution based on modified alopex al...
详细信息
ISBN:
(纸本)9783037853191
alopex is a heuristic and optimum algorithm. A self-adaptive and variable step length alopex algorithm was raised to exceed local optimal solution and to approximate global optimal solution based on modified alopex algorithm. To improve modified alopex approximation precision further and eliminate the follow-on shocks appearance, the reasonable alter of delta(in) was implemented. The simulation results show algorithm optimized is practicable and effective.
It is difficult to determine the recognition mechanism in the neurons of a neural network trained for pattern recognition due to the non-linear nature of neural networks. This paper describes a recognition mechanism o...
详细信息
It is difficult to determine the recognition mechanism in the neurons of a neural network trained for pattern recognition due to the non-linear nature of neural networks. This paper describes a recognition mechanism of a four-layer back propagation neural network using alopex algorithm. We have developed a small-scale, four-layered neural network model for simple character recognition, which can recognize the patterns transformed by affined conversion. alopex algorithm is an iterative and stochastic processing method, which was proposed for optimization of a given cost function. In this case the receptive fields of the neurons in the output layers are obtained using the alopex algorithm.
To solve dynamic optimization problem of chemical process (CPDOP), a hybrid differential evolution algorithm, which is integrated with alopex and named as alopex-DE, was proposed. In alopex-DE, each original individua...
详细信息
To solve dynamic optimization problem of chemical process (CPDOP), a hybrid differential evolution algorithm, which is integrated with alopex and named as alopex-DE, was proposed. In alopex-DE, each original individual has its own symbiotic individual, which consists of control parameters. Differential evolution operator is applied for the original individuals to search the global optimization solution. alopex algorithm is used to co-evolve the symbiotic individuals during the original individual evolution and enhance the fitness of the original individuals. Thus, control parameters are self-adaptively adjusted by alopex to obtain the real-time optimum values for the original population. To illustrate the whole performance of alopex-DE, several varietal DEs were applied to optimize 13 benchmark functions. The results show that the whole performance of alopex-DE is the best. Further, alopex-DE was applied to solve 4 typical CPDOPs, and the effect of the discrete time degree on the optimization solution was analyzed. The satisfactory result is obtained.
Idle speed control in a fuel-injection engine system has focused on controlling long-term averages of engine speed, but short-term fluctuations of engine speed have been neglected. The torque differences among cylinde...
详细信息
Idle speed control in a fuel-injection engine system has focused on controlling long-term averages of engine speed, but short-term fluctuations of engine speed have been neglected. The torque differences among cylinders influence the idle stability and cause vibration of the vehicle. In this paper, we introduce two intelligent control systems to reduce the fluctuations of engine speed at idle, an evolutionary computing control based on genetic algorithms and a stochastic control based on alopex algorithm. We first estimate the torque differences among the cylinders by observing an engine cycle of crankshaft angular speed. Then the uniformity level over the engine speed is fedback into the control system. It manipulates spark ignition timings to suppress unbalanced combustions among the cylinders. We test the two adaptive approaches with simulation of a nonlinear engine model, and compare their performances. (C) 2007 Elsevier Inc. All rights reserved.
We present computer simulations of a tip-tilt adaptive optics system, where stochastic optimization is applied to the problem of dynamic compensation of atmospheric turbulence. The system uses a simple measure of the ...
详细信息
We present computer simulations of a tip-tilt adaptive optics system, where stochastic optimization is applied to the problem of dynamic compensation of atmospheric turbulence. The system uses a simple measure of the light intensity that passes through a mask and is recorded on the image plane, to generate signals for the tip-tilt mirror. A feedback system rotates the mirror adaptively and in phase with the rapidly changing atmospheric conditions. Computer simulations and a series of numerical experiments investigate the implementation of the method in the presence of drifting atmosphere. In particular, the study examines the system's sensitivity to the rate of change of the atmospheric conditions and investigates the optimal size of the mirror's masking area and the algorithm's optimal degree of stochasticity. (C) 2002 Elsevier Science B.V. All rights reserved.
This paper addresses stochastic correlative learning as the basis for a broadly defined class of statistical learning algorithms known collectively as the algorithm of pattern extraction (alopex) family. Starting with...
详细信息
This paper addresses stochastic correlative learning as the basis for a broadly defined class of statistical learning algorithms known collectively as the algorithm of pattern extraction (alopex) family. Starting with the neurobiologically motivated Hebb's rule, the two conventional forms of the alopex algorithm,are derived, followed by a modified variant designed to improve the convergence speed. We next describe two more elaborate versions of the alopex algorithm, which incorporate particle filtering that exemplifies a form of Monte Carlo simulation, to exchange computational complexity for an improved convergence and tracking behavior. In support of the different forms of the alopex algorithm developed herein, we present three different experiments using synthetic and real-life data on binocular fusion of stereo images, on-line prediction, and system identification.
Considering that it is difficult to set suitable penalty factors for the penalty function method, which is one of the most important ways to solve constrained optimization problems, and that the quality of obtained op...
详细信息
Considering that it is difficult to set suitable penalty factors for the penalty function method, which is one of the most important ways to solve constrained optimization problems, and that the quality of obtained optimal solution mainly depends on the optimization algorithm's performance and handling constraints capacity, a novel differential evolution algorithm with co-evolution of control parameters and penalty factors, named as CoE-DE, is proposed. In CoE-DE, differential evolution operator is applied for evolving the original individuals, which consist of optimal variables. To improve the performance of CoE-DE and the handling constraints capacity, alopex algorithm is used to co-evolve the symbiotic individuals, which consist of two DE control parameters and the penalty factors. To illustrate the whole performance of CoE-DE, several algorithms are applied to solve 13 benchmark functions and five constrained engineering problems. The results show that the performance of CoE-DE is better than SR algorithm and similar to a SIMPILE in 13 benchmark functions, and the satisfactory result is obtained in five constrained engineering problems. Copyright (C) 2010 Curtin University of Technology and John Wiley & Sons, Ltd.
We have investigated the performance of an adaptive optics system subjected to changing atmospheric conditions, under the guidance of the alopex stochastic optimization. Atmospheric distortions are smoothed out by mea...
详细信息
We have investigated the performance of an adaptive optics system subjected to changing atmospheric conditions, under the guidance of the alopex stochastic optimization. Atmospheric distortions are smoothed out by means of a deformable mirror, the shape of which can be altered in order to follow the rapidly changing atmospheric phase fluctuations. In a simulation model, the total intensity of the light measured on a central area of the image (masking area) is used as the cost function for our stochastic optimization algorithm, while the surface of the deformable mirror is approximated by a Zernike polynomial expansion. Atmospheric turbulence is simulated by a number of Kolmogorov filters. The method's effectiveness, that is its ability to follow the motion of the turbulent wavefronts, is studied in detail and as it pertains to the size of the mirror's masking area, to the number of Zernike polynomials used and to the degree of the algorithm's stochasticity in relation to the mean rate of change of atmospheric distortions. Computer simulations and a series of numerical experiments are reported to show the successful implementation of the method.
Based on an alopex optimization algorithm and a response surface model(RSM),a hybrid sub-region methodology is presented to solve the optimal design problems of permanent magnet(PM)*** alopex optimization method is pr...
详细信息
Based on an alopex optimization algorithm and a response surface model(RSM),a hybrid sub-region methodology is presented to solve the optimal design problems of permanent magnet(PM)*** alopex optimization method is processed both in subspace and in global solution *** order to decrease the computing time,a multi quadric radial basis function(MQRBF)is embedded in the *** proposed method speeds up the convergence rate while keeps the accuracy of the solution.A numerical experiment is given to validate the efficiency and effectiveness of the method.
暂无评论