Search

This paper presents a fully complex-valued relaxation network (FCRN) with its projection-based learning algorithm. The FCRN is a single hidden layer network with a Gaussian-like sech activation function in the hidden layer and an exponential activation function in the output layer. For a given number of hidden neurons, the input weights are assigned randomly and the output weights are estimated by minimizing a nonlinear logarithmic function (called as an energy function) which explicitly contains both the magnitude and phase errors. A projection-based learning algorithm determines the optimal output weights corresponding to the minima of the energy function by converting the nonlinear programming problem into that of solving a set of simultaneous linear algebraic equations. The resultant FCRN approximates the desired output more accurately with a lower computational effort. The classification ability of FCRN is evaluated using a set of real-valued benchmark classification problems from the University of California, Irvine machine learning repository. Here, a circular transformation is used to transform the real-valued input features to the complex domain. Next, the FCRN is used to solve three practical problems: a quadrature amplitude modulation channel equalization, an adaptive beamforming, and a mammogram classification. Performance results from this paper clearly indicate the superior classification/approximation performance of the FCRN.

This paper presents a meta-cognitive learning algorithm for a single hidden layer complex-valued neural network called "Meta-cognitive Fully Complex-valued Relaxation Network (McFCRN)". McFCRN has two components: a cognitive component and a meta-cognitive component. A Fully Complex-valued Relaxation Network (FCRN) with a fully complex-valued Gaussian like activation function (sech) in the hidden layer and an exponential activation function in the output layer forms the cognitive component. The meta-cognitive component contains a self-regulatory learning mechanism which controls the learning ability of FCRN by deciding what-to-learn, when-to-learn and how-to-learn from a sequence of training data. The input parameters of cognitive components are chosen randomly and the output parameters are estimated by minimizing a logarithmic error function. The problem of explicit minimization of magnitude and phase errors in the logarithmic error function is converted to system of linear equations and output parameters of FCRN are computed analytically. McFCRN starts with zero hidden neuron and builds the number of neurons required to approximate the target function. The meta-cognitive component selects the best learning strategy for FCRN to acquire the knowledge from training data and also adapts the learning strategies to implement best human learning components. Performance studies on a function approximation and real-valued classification problems show that proposed McFCRN performs better than the existing results reported in the literature., (Copyright © 2012 Elsevier Ltd. All rights reserved.)

This paper presents a sequential learning algorithm for a complex-valued resource allocation network with a self-regulating scheme, referred to as complex-valued self-regulating resource allocation network (CSRAN). The self-regulating scheme in CSRAN decides what to learn, when to learn, and how to learn based on the information present in the training samples. CSRAN is a complex-valued radial basis function network with a sech activation function in the hidden layer. The network parameters are updated using a complex-valued extended Kalman filter algorithm. CSRAN starts with no hidden neuron and builds up an appropriate number of hidden neurons, resulting in a compact structure. Performance of the CSRAN is evaluated using a synthetic complex-valued function approximation problem, two real-world applications consisting of a complex quadrature amplitude modulation channel equalization, and an adaptive beam-forming problem. Since complex-valued neural networks are good decision makers, the decision-making ability of the CSRAN is compared with other complex-valued classifiers and the best performing real-valued classifier using two benchmark unbalanced classification problems from UCI machine learning repository. The approximation and classification results show that the CSRAN outperforms other existing complex-valued learning algorithms available in the literature.

In this paper, a fully complex-valued radial basis function (FC-RBF) network with a fully complex-valued activation function has been proposed, and its complex-valued gradient descent learning algorithm has been developed. The fully complex activation function, sech(.) of the proposed network, satisfies all the properties needed for a complex-valued activation function and has Gaussian-like characteristics. It maps C(n) --> C, unlike the existing activation functions of complex-valued RBF network that maps C(n) --> R. Since the performance of the complex-RBF network depends on the number of neurons and initialization of network parameters, we propose a K-means clustering based neuron selection and center initialization scheme. First, we present a study on convergence using complex XOR problem. Next, we present a synthetic function approximation problem and the two-spiral classification problem. Finally, we present the results for two practical applications, viz., a non-minimum phase equalization and an adaptive beam-forming problem. The performance of the network was compared with other well-known complex-valued RBF networks available in literature, viz., split-complex CRBF, CMRAN and the CELM. The results indicate that the proposed fully complex-valued network has better convergence, approximation and classification ability.

In this paper, the recently developed Extreme Learning Machine (ELM) is used for direct multicategory classification problems in the cancer diagnosis area. ELM avoids problems like local minima, improper learning rate and overfitting commonly faced by iterative learning methods and completes the training very fast. We have evaluated the multi-category classification performance of ELM on three benchmark microarray datasets for cancer diagnosis, namely, the GCM dataset, the Lung dataset and the Lymphoma dataset. The results indicate that ELM produces comparable or better classification accuracies with reduced training time and implementation complexity compared to artificial neural networks methods like conventional back-propagation ANN, Linder's SANN, and Support Vector Machine methods like SVM-OVO and Ramaswamy's SVM-OVA. ELM also achieves better accuracies for classification of individual categories.

This paper presents a simple sequential growing and pruning algorithm for radial basis function (RBF) networks. The algorithm referred to as growing and pruning (GAP)-RBF uses the concept of "Significance" of a neuron and links it to the learning accuracy. "Significance" of a neuron is defined as its contribution to the network output averaged over all the input data received so far. Using a piecewise-linear approximation for the Gaussian function, a simple and efficient way of computing this significance has been derived for uniformly distributed input data. In the GAP-RBF algorithm, the growing and pruning are based on the significance of the "nearest" neuron. In this paper, the performance of the GAP-RBF learning algorithm is compared with other well-known sequential learning algorithms like RAN, RANEKF, and MRAN on an artificial problem with uniform input distribution and three real-world nonuniform, higher dimensional benchmark problems. The results indicate that the GAP-RBF algorithm can provide comparable generalization performance with a considerably reduced network size and training time.

Training set parallelism and network based parallelism are two popular paradigms for parallelizing a feedforward (artificial) neural network. Training set parallelism is particularly suited to feedforward neural networks with backpropagation learning where the size of the training set is large in relation to the size of the network. This paper analyzes training set parallelism for feedforward neural networks when implemented on a transputer array configured in a pipelined ring topology. Theoretical expressions for the time per epoch (iteration) and optimal size of a processor network are derived when the training set is equally distributed among the processing nodes. These show that the speed up is a function of the number of patterns per processor, communication overhead per epoch and the total number of processors in the topology. Further analysis of how to optimally distribute the training set on a given processor network when the number of patterns in the training set is not an integer multiple of the number of processors, is also carried out. It is shown that optimal allocation of patterns in such cases is a mixed integer programming problem. Using this analysis it is found that equal distribution of training patterns among the processors is not the optimal way to allocate the patterns even when the training set is an integer multiple of the number of processors. Extension of the analysis to processor networks comprising processors of different speeds is also carried out. Experimental results from a T805 transputer array are presented to verify all the theoretical results.

Abstract: This paper presents a new sequential multi-category classifier using radial basis function (SMC-RBF) network for real-world classification problems. The classification algorithm processes the training data one by one and builds the RBF network starting with zero hidden neuron. The growth criterion uses the misclassification error, the approximation error to the true decision boundary and a distance measure between the current sample and the nearest neuron belonging to the same class. SMC-RBF uses the hinge loss function (instead of the mean square loss function) for a more accurate estimate of the posterior probability. For network parameter updates, a decoupled extended Kalman filter is used to reduce the computational overhead. Performance of the proposed algorithm is evaluated using three benchmark problems, viz., image segmentation, vehicle and glass from the UCI machine learning repository. In addition, performance comparison has also been done on two real-world problems in the areas of remote sensing and bio-informatics. The performance of the proposed SMC-RBF classifier is also compared with the other RBF sequential learning algorithms like MRAN, GAP-RBFN, OS-ELM and the well-known batch classification algorithm SVM. The results indicate that SMC-RBF produces a higher classification accuracy with a more compact network. Also, the study indicates that using a function approximation algorithm for classification problems may not work well when the classes are not well separated and the training data is not uniformly distributed among the classes. [Copyright &y& Elsevier]

Abstract: Recently, a new learning algorithm for the feedforward neural network named the extreme learning machine (ELM) which can give better performance than traditional tuning-based learning methods for feedforward neural networks in terms of generalization and learning speed has been proposed by Huang et al. In this paper, we first extend the ELM algorithm from the real domain to the complex domain, and then apply the fully complex extreme learning machine (C-ELM) for nonlinear channel equalization applications. The simulation results show that the ELM equalizer significantly outperforms other neural network equalizers such as the complex minimal resource allocation network (CMRAN), complex radial basis function (CRBF) network and complex backpropagation (CBP) equalizers. C-ELM achieves much lower symbol error rate (SER) and has faster learning speed. [Copyright &y& Elsevier]