In this paper, we present an efficient technique for mapping a backpropagation (BP) learning algorithm for multilayered neural networks onto a network of workstations (NOW's). We adopt a vertical partitioning sche...
详细信息
In this paper, we present an efficient technique for mapping a backpropagation (BP) learning algorithm for multilayered neural networks onto a network of workstations (NOW's). We adopt a vertical partitioning scheme, where each layer in the neural network is divided into p disjoint partitions, and map each partition onto an independent workstation in a network of p workstations. We present a fully distributed version of the BP algorithm and also its speedup analysis. We compare the performance of our algorithm with a recent work involving the vertical partitioning approach for mapping the BP algorithm onto a distributed memory multiprocessor. Our results on SUN 3/50 NOW's show that we are able to achieve better speedups by using only two communication sets and also by avoiding some redundancy in the weights computation for one training cycle of the algorithm.
It is essential to develop an accurate model of proton exchange membrane fuel cell (PEMFC) for a reliable operation and analysis, in which unknown parameters usually need to be determined. The inherent nonlinear, stro...
详细信息
It is essential to develop an accurate model of proton exchange membrane fuel cell (PEMFC) for a reliable operation and analysis, in which unknown parameters usually need to be determined. The inherent nonlinear, strong coupling, and diversification of PEMFC model seriously hinder traditional methods to identify the parameters. For the sake of overcoming these thorny obstacles, Levenberg-Marquardt backpropagation (LMBP) algorithm based on artificial neural networks (ANNs) is proposed for PEMFC parameter identification. Furthermore, the performance of LMBP is thoroughly evaluated and compared with four typical meta-heuristic algorithms under three cases. Simulation results indicate that LMBP performs a higher accuracy and faster speed for parameter identification. In particular, accuracy and convergence speed can achieve as much as 99.8% and 95.9% growth via LMBP, respectively. (c) 2021 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved.
The backpropagation algorithm is one of the most used tools for training artificial neural networks. However, this tool may be very slow in some practical applications. Many techniques have been discussed to speed up ...
详细信息
The backpropagation algorithm is one of the most used tools for training artificial neural networks. However, this tool may be very slow in some practical applications. Many techniques have been discussed to speed up the performance of this algorithm and allow its use in an even broader range of applications. Although the backpropagation algorithm has been used for decades, we present here a set of computational results that suggest that by replacing bihyperbolic functions the backpropagation algorithm performs better than the traditional sigmoid functions. To the best of our knowledge, this finding was never previously published in the open literature. The efficiency and discrimination capacity of the proposed methodology are shown through a set of computational experiments, and compared with the traditional problems of the literature.
In this paper, we present a new technique for mapping the backpropagation algorithm on hypercubes and related architectures. A key component of this technique is a network partitioning scheme called checkerboarding, C...
详细信息
In this paper, we present a new technique for mapping the backpropagation algorithm on hypercubes and related architectures. A key component of this technique is a network partitioning scheme called checkerboarding, Checkerboarding allows ns to replace the ail-to-all broadcast operation performed by the commonly used vertical network partitioning scheme, with operations that are much faster on the hypercubes and related architectures. Checkerboarding can be combined with the pattern partitioning technique to form a hybrid scheme that performs better than either one of these schemes. Theoretical analysis and experimental results on nCUBE(R) and CM5(R) show that our scheme performs better than the other schemes, for both uniform and nonuniform networks.
Since the traditional probabilistic neural network (PNN) cannot systematically solve the difficulty of estimating probability function and the high space complexity, this paper introduces backpropagation (BP) algorith...
详细信息
Since the traditional probabilistic neural network (PNN) cannot systematically solve the difficulty of estimating probability function and the high space complexity, this paper introduces backpropagation (BP) algorithm into the classical PNN. By designing appropriate error function and BP algorithm based on the steepest descent, an improved BP-PNN is presented, with its algorithm and effectiveness deduced. Three synthetic datasets and ten benchmark problems have been tested, compared with Probabilistic Neural Networks (PNN), Multi-Layered Perceptron (MLP) and Support Vector Machine (SVM). The results prove that (1) the accuracy of classification of BP-PNN is much higher than PNN, and it has a significant advantage compared with MLP and SVM;(2) BP-PNN has strong capacity to identify the importance of input indicators;(3) BP-PNN is a new pattern classification method to estimate the probabilistic function, reduce the space complexity and identify the importance of the indicators.
A fast learning rule for artificial neural systems which is based on modifications to a backpropagation algorithm is described. The rule minimises the error function along the direction of the gradient and backpropaga...
详细信息
A fast learning rule for artificial neural systems which is based on modifications to a backpropagation algorithm is described. The rule minimises the error function along the direction of the gradient and backpropagates the error pattern according to a constant error energy approach.
Neural networks have recently attracted much attention due to the development of artificial intelligence or deep learning technology. These can be implemented by applying the current hardware technology such as a cent...
详细信息
Neural networks have recently attracted much attention due to the development of artificial intelligence or deep learning technology. These can be implemented by applying the current hardware technology such as a central processing unit and a graphics processing unit. In this case, the applications are limited because considerable power and large volume are used. To overcome these shortcomings, hardware development for artificial intelligence is accelerated, and this technology is called the neuromorphic system, which is especially suitable for low-power and small-area applications such as wearable devices. In this study, the neuromorphic system is implemented using the field-programmable gate array (FPGA), and it is applied to wearable systems. This system is especially developed for a module that measures the drowsiness of a user based on biosignals such as electrocardiogram (ECG) and electromyography (EMG). The measured biosignals are fed to the neuromorphic system for supervised learning using the backpropagation algorithm. Therefore, it is possible to make the drowsiness driving assessment specific to each user, and the error on the user's condition can be minimized. In addition, by integrating artificial intelligence including learning algorithm and biosensor circuits, it is possible to minimize disturbance to the driver or user through miniaturization and low power consumption.
Artificial neural networks are commonly known as Universal Approximators;a property immensely useful in system identification and control applications. Traditionally, neural networks are trained with gradient-descent ...
详细信息
ISBN:
(纸本)9781538675366
Artificial neural networks are commonly known as Universal Approximators;a property immensely useful in system identification and control applications. Traditionally, neural networks are trained with gradient-descent backpropagation algorithms. However, these algorithms are computationally burdened and slow due to the calculation of error derivatives. As a result, the research focus has shifted to develop gradient-free neural algorithms. One famous approach is to incorporate Lyapunov Functions in network parameter optimization. In this paper, we briefly discuss and analyze one such recently developed algorithm from the point-of-view of its applicability in adaptive control paradigm. It has been found that with a few proposed modifications, this algorithm can work excellently as neuroadaptive inverse controller.
In this paper, we investigate proper strategies for determining the step size of the backpropagation (BP) algorithm for on-line learning. It is known that for off-line learning, the step size can be determined adaptiv...
详细信息
ISBN:
(纸本)9781467393607
In this paper, we investigate proper strategies for determining the step size of the backpropagation (BP) algorithm for on-line learning. It is known that for off-line learning, the step size can be determined adaptively during learning. For on-line learning, since the same data may never appear again, we cannot use the same strategy proposed for off-line learning. If we do not update the neural network with a proper step size for on-line learning, the performance of the network may not be improved steadily. Here, we investigate four strategies for updating the step size. They are 1) constant, 2) random, 3) linearly decreasing, and 4) inversely proportional, respectively. The first strategy uses a constant step size during learning, the second strategy uses a random step size, the third strategy decreases the step size linearly, and the fourth strategy updates the step size inversely proportional to time. Experimental results show that, the third and the fourth strategies are more effective. In addition, compared with the third strategy, the fourth one is more stable, and usually can improve the performance steadily.
Natural hazards generate disasters and huge losses in several aspects, with landslides being one of the natural risks that have caused great impacts worldwide. The aim of this research was to explore a method based on...
详细信息
Natural hazards generate disasters and huge losses in several aspects, with landslides being one of the natural risks that have caused great impacts worldwide. The aim of this research was to explore a method based on machine learning to evaluate susceptibility to rotational landslides in an area near Cuenca city, Ecuador, which has a high incidence of these phenomena, mainly due to its environmental conditions, and in which, however, such studies are scarce. The implemented method consisted of an artificial neural network multilayer perceptron (ANN MLP), generated with the neuralnet R package, with which, by means of different backpropagation algorithms (RPROP+, RPROP-, SLR, SAG, and Backprop), five landslide susceptibility maps (LSMs) were generated for the study area. A landslide inventory updated to 2019 and 10 conditioning factors, mainly topographical, geological, land cover, and hydrological, were considered. The results obtained, which were validated through the AUC-ROC value and statistical parameters of precision, recall, accuracy, and F-Score, showed a good degree of adjustment and an acceptable predictive capacity. The resulting maps showed that the area has mostly sectors of moderate, high, and very high susceptibility, whose landslide occurrence percentages vary between approximately 63% and 80%. In this research, different variants of the backpropagation algorithm were implemented to verify which one gave the best results. With the implementation of additional methodologies and correct zoning, future analyses could be developed, contributing to adequate territorial planning and better disaster risk management in the area.
暂无评论