Complex-valued associative memories (CAMs) are one of the most promising associative memory models by neural networks. However, the low noise tolerance of CAMs is often a serious problem. A projection learning rule wi...
详细信息
Complex-valued associative memories (CAMs) are one of the most promising associative memory models by neural networks. However, the low noise tolerance of CAMs is often a serious problem. A projection learning rule with large constant terms improves the noise tolerance of CAMs. However, the projection learning rule can be applied only to CAMs with full connections. In this paper, we propose a gradient descent learning rule with large constant terms, which is not restricted by network topology. We realize large constant terms by regularization to connection weights. By computer simulations, we prove that the proposed learning algorithm improves noise tolerance. (c) 2016 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.
Exploiting multi-core architectures is a way to tackle the CPU time consumption when solving SATisfiability (SAT) problems. Portfolio is one of the main techniques that implements this principle. It consists in making...
详细信息
Exploiting multi-core architectures is a way to tackle the CPU time consumption when solving SATisfiability (SAT) problems. Portfolio is one of the main techniques that implements this principle. It consists in making several solvers competing, on the same problem, and the winner will be the first that answers. In this work, we improved this technique by using a learning schema, namely the Exploration-Exploitation using Exponential weight (EXP3), that allows smart resource allocations. Our contribution is adapted to situations where we have to solve a bench of SAT instances issued from one or several sequence of problems. Our experiments show that our approach achieves good results.
In this paper, a novel learning algorithm of wavelet networks based on the Fast Wavelet Transform (FWT) is proposed. It has many advantages compared to other algorithms, in which we solve the problem in previous works...
详细信息
In this paper, a novel learning algorithm of wavelet networks based on the Fast Wavelet Transform (FWT) is proposed. It has many advantages compared to other algorithms, in which we solve the problem in previous works, when the weights of the hidden layer to the output layer are determined by applying the back propagation algorithm or by direct solution which requires to compute the matrix inversion, this may cause intensive computation when the learning data is too large. However, the new algorithm is realized by iterative application of FWT to compute the connection weights. Furthermore, we have extended the novel learning algorithm by using Levenberg - Marquardt method to optimize the learning functions. The experimental results have demonstrated that our model is remarkably more refreshing than some of the previously established models in terms of both speed and efficiency.
This paper presents a new approach of face recognition based on wavelet network using 2D fast wavelet transform and multiresolution analysis. This approach is divided in two stages: the training stage and the recognit...
详细信息
This paper presents a new approach of face recognition based on wavelet network using 2D fast wavelet transform and multiresolution analysis. This approach is divided in two stages: the training stage and the recognition stage. The first consists to approximate every training face image by a wavelet network. The second consists in recognition of a new test image by comparing it to all the training faces, the distances between this test face and all images from the training set are calculated in order to identify the searched person. The usual training algorithms presents some disadvantages when the weights of the wavelet network are computed by applying the back-propagation algorithm or by direct solution which requires computing an inversion of matrix, this computation may be intensive when the learning data is too large. We present in this paper our solutions to overcome these limitations. We propose a novel learning algorithm based on the 2D Fast Wavelet Transform. Furthermore, we have increased the performances of our algorithm by introducing the Levenberg-Marquardt method to optimize the learning functions and using the Beta wavelet which has at both an analytical expression and wavelet filter bank. Extensive empirical experiments are performed to compare the proposed method with other approaches as PCA, LDA, EBGM and RBF neural network using the ORL and FERET benchmarks.
This paper presents a novel design of interval type-2 fuzzy logic systems (IT2FLS) by utilizing the theory of extreme learning machine (ELM) for electricity load demand forecasting. ELM has become a popular learning a...
详细信息
This paper presents a novel design of interval type-2 fuzzy logic systems (IT2FLS) by utilizing the theory of extreme learning machine (ELM) for electricity load demand forecasting. ELM has become a popular learning algorithm for single hidden layer feed-forward neural networks (SLFN). From the functional equivalence between the SLFN and fuzzy inference system, a hybrid of fuzzy-ELM has gained attention of the researchers. This paper extends the concept of fuzzy-ELM to an IT2FLS based on ELM (IT2FELM). In the proposed design the antecedent membership function parameters of the IT2FLS are generated randomly, whereas the consequent part parameters are determined analytically by the Moore Penrose pseudo inverse. The ELM strategy ensures fast learning of the IT2FLS as well as optimality of the parameters. Effectiveness of the proposed design of IT2FLS is demonstrated with the application of forecasting nonlinear and chaotic data sets. Nonlinear data of electricity load from the Australian National Electricity Market for the Victoria region and from the Ontario Electricity Market are considered here. The proposed model is also applied to forecast Mackey-glass chaotic time series data. Comparative analysis of the proposed model is conducted with some traditional models such as neural networks (NN) and adaptive neuro fuzzy inference system (ANFIS). In order to verify the structure of the proposed design of IT2FLS an alternate design of IT2FLS based on Kalman filter (KF) is also utilized for the comparison purposes. (C) 2016 Elsevier Ltd. All rights reserved.
Aimed at the problem of deviation of uncertainty estimates in the test model of attributes selecting with the information gain,an improved learning algorithm of decision tree based on the uncertainty deviation of entr...
详细信息
ISBN:
(纸本)9781467321006
Aimed at the problem of deviation of uncertainty estimates in the test model of attributes selecting with the information gain,an improved learning algorithm of decision tree based on the uncertainty deviation of entropy measure was *** the algorithm,the method of regulating oppositely deviation of the information entropy peak through a sine function was used,when test of attributes choice with information gain the adverse effect of deviation of information entropy peak was *** with the ID3,the improvement of classification performance was acquired while its better stability of performance for its decision *** research results show that the rationality of attribute selection test was effectively improved through the method based on the entropy uncertainty deviation.
Fitting of forecast function is very difficult and important in non-linear regression forecast problems. The accuracy is directly affected by the fitting of forecast function. Linear model replaced non-linear model in...
详细信息
ISBN:
(纸本)9783037850091
Fitting of forecast function is very difficult and important in non-linear regression forecast problems. The accuracy is directly affected by the fitting of forecast function. Linear model replaced non-linear model in the traditional method is difficult to solve the problem when non-linear is stronger, and the result of fitting and forecast is not ideal. Functional network is a recently introduced extension of neural networks. It has certain advantages solving non-linear problems. Non-linear regression forecast model and learning algorithm based on functional networks is proposed in this article. Example about multi-variable non-linear regression forecast is provided. The simulation results demonstrate that forecast model based on Functional Networks whose accuracy of fitting and forecasting is more than some traditional methods have some value about theory and application.
In the present paper, using generalizations of the fuzzy integral equations for interval-valued fuzzy sets, we introduce and study new generalized interval-valued fuzzy linear Fredholm integral equation concepts. The ...
详细信息
In the present paper, using generalizations of the fuzzy integral equations for interval-valued fuzzy sets, we introduce and study new generalized interval-valued fuzzy linear Fredholm integral equation concepts. The work of this paper is an expansion of the research of real fuzzy linear Fredholm integral equations. In this paper interval-valued fuzzy neural network (IVFNN) can be trained with crisp and interval-valued fuzzy data. In this paper, a novel hybrid method based on IVFNN and Newton-Cotes methods with positive coefficient for the solution of interval-valued fuzzy linear Fredholm integral equations (IVFLFIEs) of the second kind is presented. Within this paper the fuzzy neural network model is used to obtain an estimate for the fuzzy parameters in a statistical sense. Then a simple algorithm from the cost function of the interval-valued fuzzy neural network is proposed, in order to find the approximate parameters. We propose a learning algorithm from the cost function for adjusting of interval valued fuzzy weights. Here neural network is considered as a part of a larger field called neural computing or soft computing. Finally, we illustrate our approach by some numerical examples. (C) 2016 Elsevier B.V. All rights reserved.
Next generation mobile networks will face the unprecedented demand for higher data rates. To satisfy this demand, the dense deployment of heterogeneous wireless networks (HetNets) is a promising solution. One of the m...
详细信息
ISBN:
(纸本)9781479966646
Next generation mobile networks will face the unprecedented demand for higher data rates. To satisfy this demand, the dense deployment of heterogeneous wireless networks (HetNets) is a promising solution. One of the major challenges in dense HetNets is to dynamically allocate the resources such as power and channel so that the energy efficiency and throughput of the network improve. One of the important techniques for improving the energy efficiency of the base station (BS) is BS ON-OFF switching which allows the BS to turn off some of its components in lower load situations. On the other side, due to the proximity of BSs in the dense HetNets, co-channel interference (CCI) becomes a critical problem and significantly impacts the performance of the network. In this paper, we propose a dynamic channel assignment based on a learning algorithm (DCA-LA). Moreover, we combine DCA-LA with a BS ON-OFF switching algorithm in order to improve the energy efficiency of the system. In particular, the proposed DCA-LA/ON-OFF switching algorithm is self-organizing and performs in a fully distributed manner. Simulation results indicate that our proposed algorithm balances load among BSs and yields better performance in terms of average energy consumption, average load, average utility per BS and average rate per user, compared to the baseline algorithms.
In this paper, a novel hybrid method based on interval-valued fuzzy neural network for approximate of interval-valued fuzzy regression models, is presented. The work of this paper is an expansion of the research of re...
详细信息
In this paper, a novel hybrid method based on interval-valued fuzzy neural network for approximate of interval-valued fuzzy regression models, is presented. The work of this paper is an expansion of the research of real fuzzy regression models. In this paper interval-valued fuzzy neural network (IVFNN) can be trained with crisp and interval-valued fuzzy data. Here a neural network is considered as a part of a large field called neural computing or soft computing. Moreover, in order to find the approximate parameters, a simple algorithm from the cost function of the fuzzy neural network is proposed. Finally, we illustrate our approach by some numerical examples and compare this method with existing methods.
暂无评论