In this paper the comparison of a proposed neural network with generalized type-2 fuzzy weights (NNGT2FW) with respect to the monolithic neural network (NN) and the neural network with interval type-2 fuzzy weights (N...
详细信息
In this paper the comparison of a proposed neural network with generalized type-2 fuzzy weights (NNGT2FW) with respect to the monolithic neural network (NN) and the neural network with interval type-2 fuzzy weights (NNIT2FW) is presented. Generalized type-2 fuzzy inference systems are used to obtain the generalized type-2 fuzzy weights and are designed by a strategy of increasing and decreasing an epsilon variable for obtaining the different sizes of the footprint of uncertainty (FOU) for the generalized membership functions. The proposed method is based on recent approaches that handle weight adaptation using type-1 and type-2 fuzzy logic. The approach is applied to the prediction of the Mackey-Glass time series, and results are shown to outperform the results produced by other neural models. Gaussian noise was applied to the test data of the Mackey-Glass time series for finding out which of the presented methods in this paper shows better performance and tolerance to noise. (C) 2015 Elsevier Inc. All rights reserved.
The research proposes a new method to solve the spectrum aliasing and improve the resolution of off-axis digital holograms based on Kronecker interpolation and backpropagation algorithms. The method suppresses the dir...
详细信息
The research proposes a new method to solve the spectrum aliasing and improve the resolution of off-axis digital holograms based on Kronecker interpolation and backpropagation algorithms. The method suppresses the direct current (DC) image and increase the low-frequency information with Kronecker interpolation of the hologram. The size of the Fresnel reconstructed image can be controlled with the reconstruction distance, and this feature is used to select the appropriate reconstruction distance for the Fresnel amplitude reconstruction of interpolated holograms to separate the real and imaginary images. To obtain the complete first-order spectral information for the object, the amplitude of the desired image is obtained with spatial domain filtering and then inverted. Finally, the amplitude and phase of the object are reconstructed according to the angular spectrum reconstruction algorithm. The results show that the method can solve the spectrum aliasing problem of the holograms and thus improve the resolution of off-axis holograms. In addition, the background noise of the reconstructed phase is reduced because the influence of the zero-order spectrum can be completely avoided.
Neural networks utilize the paradigm of the human brain to acquire knowledge through a training process. The knowledge base is stored in the form of weighted interconnections between layer nodes;this allows the networ...
详细信息
Neural networks utilize the paradigm of the human brain to acquire knowledge through a training process. The knowledge base is stored in the form of weighted interconnections between layer nodes;this allows the network to generalize. Computational experimentation with a back-propagation algorithm yielded useful information concerning the effect of several key model parameters on network training and performance. These findings are illustrated through the application of a modest sized three layer neural network to the planning of end user involvement in the development of information systems.
作者：
Amin, ShohelCoventry Univ
Sch Energy Inst Future Transport & Cities Construct & Environm Sir John Laing Bldg Coventry CV1 5FB W Midlands England
Older people are vulnerable road users with higher rate of casualties in traffic accidents. The commonly cited causes of accidents for older people are poor attention and decision making at critical locations of road,...
详细信息
Older people are vulnerable road users with higher rate of casualties in traffic accidents. The commonly cited causes of accidents for older people are poor attention and decision making at critical locations of road, poor visibility in extreme weather, poor road surface condition and unpredictability of other road users, particularly young drivers. Female drivers are often labelled as being precarious drivers and having higher accident risk comparing to male drivers. This paper applies backpropagation - Artificial Neural Network (BP-ANN) with a Generalized Delta Rule (GDR) learning algorithm to model the factors affecting traffic accidents of both older female and male drivers. The BP-ANN can construct the causation model of traffic accidents with greater accuracy and define the proportion of errors contributed by each factor to traffic accidents. This paper studies a total of 95,092 accident records in West Midlands of the United Kingdom during the period of 2006 to 2016. This paper determines journey purpose, lighting condition, pedestrian crossing with physical interventions, complex roadway geometry, extreme weather and time severity as the most significant factors of older driver accidents. The accident risk of older drivers can be improved by providing accessible routes, affordable, reliable and convenient public transport, timely warning of unexpected situations and changes in roadway geometry;increasing use of assistive technology in cars, driverless cars and encouraging active transports into sociable activities. The findings help the transport authorities and city councils to develop strategies and measures promoting public and active transports to ensuring the safety of older drivers.
We describe an approximation to backpropagation algorithm for training deep neural networks, which is designed to work with synapses implemented with memristors. The key idea is to represent the values of both the inp...
详细信息
We describe an approximation to backpropagation algorithm for training deep neural networks, which is designed to work with synapses implemented with memristors. The key idea is to represent the values of both the input signal and the backpropagated delta value with a series of pulses that trigger multiple positive or negative updates of the synaptic weight, and to use the min operation instead of the product of the two signals. In computational simulations, we show that the proposed approximation to backpropagation is well converged and may be suitable for memristor implementations of multilayer neural networks.
In this paper, a parallel deep learning-based community detection method in large complex networks (CNs) is proposed. First, a CN partitioning method is employed to divide the CN into multiple chunks to improve the ef...
详细信息
In this paper, a parallel deep learning-based community detection method in large complex networks (CNs) is proposed. First, a CN partitioning method is employed to divide the CN into multiple chunks to improve the efficiency in terms of space and time complexities. Next, the method is integrated with two optimization algorithms: (1) backpropagation (BP), which optimizes deep learning locally within each local chunk of the CN;(2) particle swarm optimization (PSO), which is used to improve the BP optimization involving all CN chunks. PSO utilizes a multi-objective function to improve the effectiveness of the proposed method. In addition, a distributed environment is set up to conduct parallel optimization of the proposed method so that multi-local optimizations could be performed simultaneously. A set of 16 real-world CNs in a range from small to large size are used to verify the effectiveness and efficiency of the method in a benchmark study. The proposed method is implemented in multi-machines with central processing unit (CPU) and graphics processing unit (GPU) devices. The results reveal the effective role of the proposed deep learning with hybrid BP-PSO optimization in detecting communities in large CNs, which requires minimum execution time on both CPU and GPU devices.(c) 2022 Elsevier Inc. All rights reserved.
Convergence rate of training algorithms for neural networks is heavily affected by initialization of weights. In this paper, an original algorithm for initialization of weights in backpropagation neural net is present...
详细信息
Convergence rate of training algorithms for neural networks is heavily affected by initialization of weights. In this paper, an original algorithm for initialization of weights in backpropagation neural net is presented with application to character recognition. The initialization method is mainly based on a customization of the Kalman filter, translating it into Bayesian statistics terms. A metrological approach is used in this context considering weights as measurements modeled by mutually dependent normal random variables. The algorithm performance is demonstrated by reporting and discussing results of simulation trials. Results are compared with random weights initialization and other methods. The proposed method shows an improved convergence rate for the backpropagation training algorithm. (C) 2016 Elsevler B.V. All rights reserved.
In this paper a neural network learning method with lower and upper type-2 fuzzy weight adjustment is proposed. The general mathematical analysis of the proposed learning method architecture and the adaptation of the ...
详细信息
ISBN:
(纸本)9781467361293;9781467361286
In this paper a neural network learning method with lower and upper type-2 fuzzy weight adjustment is proposed. The general mathematical analysis of the proposed learning method architecture and the adaptation of the interval type-2 fuzzy weights are presented. The proposed method is based on research of recent methods that manage weight adaptation and especially type-2 fuzzy weights. In this paper the neural network architecture managing lower and upper type-2 fuzzy weights and the obtained lower and upper final results are presented. The proposed approach is applied to a case of Mackey-Glass time series prediction.
Fast development of industrial robots and its utilization by the manufacturing industries for many different applications is a critical task for the selection of robots. As a consequence, the selection process of the ...
详细信息
ISBN:
(纸本)9783319309330;9783319309323
Fast development of industrial robots and its utilization by the manufacturing industries for many different applications is a critical task for the selection of robots. As a consequence, the selection process of the robot becomes very much complicated for the potential users because they have an extensive set of parameters of the available robots. In this paper, gradient descent momentum optimization algorithm is used with backpropagation neural network prediction technique for the selection of industrial robots. Through this proposed technique maximum, ten parameters are directly considered as an input for the selection process of robot where as up to seven robot parameter data be used in the existing methods. The rank of the preferred industrial robot evaluates from the perfectly the best probable robot that specifies the most genuine benchmark of robot selection for the particular application using the proposed algorithm. Moreover, the performance of the algorithms for the robot selection is analyzed using Mean Square Error (MSE), R-squared error (RSE), and Root Mean Square Error (RMSE).
Convergence problems in the case of the generalized delta rule are discussed. A modification to the nonlinearity of processing elements is proposed which is shown to smooth the cost function to minimized during the le...
详细信息
Convergence problems in the case of the generalized delta rule are discussed. A modification to the nonlinearity of processing elements is proposed which is shown to smooth the cost function to minimized during the learning phase. A variation to the generalized delta rule learning procedure, required by the introduced modification, is discussed. Extensive tests have been performed on several examples proposed in the technical literature. The tests show the effectiveness of the proposed procedure in improving the convergence properties of the backpropagation algorithm. In particular, it was shown that the proposed modification virtually eliminates nonconvergence problems if a moderate η value is used
暂无评论