Search

The tensor completion issues have obtained a great deal of attention in the past few years. However, the data fidelity part minimizes a squared loss function, which may be inappropriate for the case of noisy one-bit observations. In this paper, we alleviate the mentioned difficulty by drawing on the experience of matrix scenarios. Based on the convex relation to $\ell _{1}$ norm of the tensor multi-rank, we propose a novel optimization model trying to recover the underlying tensor in case of one-bit observations. The feasibility of this model is proved by theoretical derivations. Furthermore, an alternating direction method of multipliers based algorithm is designed to find the solution. The numerical experiments demonstrate the effectiveness of our method. [ABSTRACT FROM AUTHOR]

In order to enable voltage ride-through operation, fast and reliable voltage dips detection is necessary. It has been noticed by the analysis of a huge number of measurement results recorded in-field, in laboratory, and obtained by simulation that the voltage dips may be characterized by specific low-order voltage harmonics pattern, which appears at the beginning and at the end of the voltage dips. This feature is named harmonic footprint. This paper proposes a new method of voltage dips detection based on harmonic footprint as part of smart algorithm for detection and classification of power quality events. The aim is to achieve reliable smart voltage dips detection in 1 ms range. Several methods for harmonic estimation in real time were compared in order to choose the optimal one. The footprint is modeled by mathematical function and applied for voltage dips smart detection using recurrent neural network. The proposed method was tested for voltage dips detection analyzing signals from measurement in the real distribution grid (680 records), computer simulations using IEEE-13 bus test grid, and testing in the laboratory. The reliability (detection rate) and speed of voltage dips detection are tested and verified. Furthermore, the future research directions for presented method are outlined. [ABSTRACT FROM AUTHOR]

Object detection plays an important role in intelligent transportation systems and intelligent vehicles. Although the topic of object detection has been studied for decades, it is still challenging to accurately detect objects under complex scenarios. The contributing factors for challenges include diversified object and background appearance, motion blur, adverse weather conditions, and complex interactions among objects. In this paper, we propose a new convolutional neural network (CNN) model for traffic object detection, by using multi-scale local and global feature representation (MFR). The proposed model consists of two components: a region proposal network that generates candidate object regions and an object detection network that incorporates multi-scale features and global information, namely MFR-CNN. These two components are jointly optimized. Once the system is trained, it can detect real-world traffic objects accurately, especially small objects and heavily occluded objects. We evaluate the proposed method on four benchmark datasets, achieving consistent improvements over the state of the art. [ABSTRACT FROM AUTHOR]

A power transformer is one of the most crucial items of equipment in the electricity supply chain. The reliability of this valuable asset is strongly dependent on the condition of its subsystems such as insulation, core, windings, bushings and tap changer. Integration of various measured parameters of these subsystems makes it possible to evaluate the overall health condition of an in-service transformer. This paper develops an artificially intelligent algorithm based on multiple general regression neural networks to combine the operating condition of various subsystems of a transformer to form a quantitative health index. The model is developed using a training set derived from four conditional boundaries based on IEEE standards, the literature and the knowledge of transformer experts. Performance of the proposed method is compared with expert classifications using a database of 345 power transformers. This shows that the proposed method is reliable and effective for condition assessment and is sensitive to poor condition of any single subsystem. [ABSTRACT FROM PUBLISHER]

A residual networks family with hundreds or even thousands of layers dominates major image recognition tasks, but building a network by simply stacking residual blocks inevitably limits its optimization ability. This paper proposes a novel residual network architecture, residual networks of residual networks (RoR), to dig the optimization ability of residual networks. RoR substitutes optimizing residual mapping of residual mapping for optimizing original residual mapping. In particular, RoR adds levelwise shortcut connections upon original residual networks to promote the learning capability of residual networks. More importantly, RoR can be applied to various kinds of residual networks (ResNets, Pre-ResNets, and WRN) and significantly boost their performance. Our experiments demonstrate the effectiveness and versatility of RoR, where it achieves the best performance in all residual-network-like structures. Our RoR-3-WRN58-4 + SD models achieve new state-of-the-art results on CIFAR-10, CIFAR-100, and SVHN, with the test errors of 3.77%, 19.73%, and 1.59%, respectively. RoR-3 models also achieve state-of-the-art results compared with ResNets on the ImageNet data set. [ABSTRACT FROM AUTHOR]

Compared with other applications in computer vision, convolutional neural networks (CNNs) have underperformed on pedestrian detection. A breakthrough was made very recently using sophisticated deep CNN (DCNN) models, with a number of handcrafted features or explicit occlusion handling mechanism. In this paper, we show that by reusing the convolutional feature maps of a DCNN model as image features to train an ensemble of boosted decision models, we are able to achieve the best reported accuracy without using specially designed learning algorithms. We empirically identify and disclose important implementation details. We also show that pixel labeling may be simply combined with a detector to boost the detection performance. By adding complementary handcrafted features such as optical flow, the DCNN-based detector can be further improved. We advance the state-of-the-art results by lowering the log-average miss rate from 11.7% to 8.9% on the Caltech data set and from 11.2% to 8.6% on the Inria data set. We also achieve a comparable result to state-of-the-art approaches on the KITTI data set. [ABSTRACT FROM AUTHOR]

In this paper, we seek to improve deep neural networks by generalizing the pooling operations that play a central role in the current architectures. We pursue a careful exploration of approaches to allow pooling to learn and to adapt to complex and variable patterns. The two primary directions lie in: (1) learning a pooling function via (two strategies of) combining of max and average pooling, and (2) learning a pooling function in the form of a tree-structured fusion of pooling filters that are themselves learned. In our experiments every generalized pooling operation we explore improves performance when used in place of average or max pooling. We experimentally demonstrate that the proposed pooling operations provide a boost in invariance properties relative to conventional pooling and set the state of the art on several widely adopted benchmark datasets. These benefits come with only a light increase in computational overhead during training (ranging from additional 5 to 15 percent in time complexity) and a very modest increase in the number of model parameters (e.g., additional 1, 9, and 27 parameters for mixed, gated, and 2-level tree pooling operators, respectively). To gain more insights about our proposed pooling methods, we also visualize the learned pooling masks and the embeddings of the internal feature responses for different pooling operations. Our proposed pooling operations are easy to implement and can be applied within various deep neural network architectures. [ABSTRACT FROM PUBLISHER]

This paper presents a neural network-based method to generate multiple images with different exposures from a single input low dynamic range (LDR) image for improved high dynamic range (HDR) imaging. The proposed algorithm consists of three steps: 1) 2-D histogram estimation; 2) neural network-based LDR images estimation; and 3) generation of an optimal set of differently exposed images. The proposed method first generates image features by estimating a patched-based 2-D histogram. The extracted features are used in an input layer of the neural network, which plays a role to select an optimal set of LDR images. A set of LDR images is generated using a curvature-based contrast enhancement method. Experimental results show that the proposed method can generate an optimal set of LDR images using neural network and provide improved HDR images. In addition, the proposed method can be implemented as a preprocessing step in most existing HDR frameworks. The proposed HDR approach is considered as a single-input method that gives almost the same performance to multiple image-based HDR method. [ABSTRACT FROM PUBLISHER]

This paper presents a possibly pioneering endeavor to tackle the Microaggregation Techniques (MATs) in secure statistical databases by resorting to the principles of associative neural networks (NNs). The prior art has improved the available solutions to the MAT by incorporating proximity information, and this approach is done by recursively reducing the size of the data set by excluding points that are farthest from the centroid and points that are closest to these farthest points. Thus, although the method is extremely effective, arguably, it uses only the proximity information while -ignoring the mutual interaction between the records. In this paper, we argue that interrecord relationships can be quantified in terms of the following two entities: 1) their "association" and 2) their "interaction." This case means that records that are not necessarily close to each other may still be "grouped," because their mutual interaction, which is quantified by invoking transitive-closure-like operations on the latter entity, could be significant, as suggested by the theoretically sound principles of NNs. By repeatedly invoking the interrecord associations and interactions, the records are grouped into sizes of cardinality "k," where k is the security parameter in the algorithm. Our experimental results, which are done on artificial data and benchmark real-life data sets, demonstrate that the newly proposed method is superior to the state of the art not only based on the Information Loss (IL) perspective but also when it concerns a criterion that involves a combination of the IL and the Disclosure Risk (DR). [ABSTRACT FROM AUTHOR]

Negative correlation learning (NCL) is a neural network ensemble learning algorithm that introduces a correlation penalty term to the cost function of each individual network so that each neural network minimizes its mean square error/MSEI together with the correlation of the ensemble. This paper analyzes NCL and reveals that the training of NCL (when λ = 1) corresponds to training the entire ensemble as a single learning machine that only minimizes the MSE without regularization. This analysis explains the reason why NCL is prone to overtitting the noise in the training set. This paper also demonstrates that tuning the correlation parameter λ in NCL by cross validation cannot overcome the overfitting problem. The paper analyzes this problem and proposes the regularized negative correlation learning (RNCL) algorithm which incorporates an additional regularization term for the whole ensemble. RNCL decomposes the ensemble's training objectives, including MSE and regularization, into a set of sub-objectives, and each sub-objective is implemented by an individual neural network. In this paper, we also provide a Bayesian interpretation for RNCL and provide an automatic algorithm to optimize regularization parameters based on Bayesian inference. The RNCL formulation is applicable to any nonlinear estimator minimizing the MSE. The experiments on synthetic as well as real-world data sets demonstrate that RNCL achieves better performance than NCL, especially when the noise level is nontrivial in the data set. [ABSTRACT FROM AUTHOR]

Generation of harmonics and the existence of wave-form pollution in power system networks are important problems facing the power utilities. The determination of harmonic currents injected into a power network by a nonlinear load is complicated when the supply voltage waveform to the load is distorted by other loads and not a pure sinusoid. This paper proposes a neural network solution to this problem. A recurrent neural network trained with the backpropagation through time training algorithm is used to find a way of distinguishing between the so-called load harmonics and supply harmonics, without disconnecting the load from the network. The advantage of this method is that only waveforms of voltages and currents have to be measured. This method is applicable for both single and three phase loads and could be fabricated into a commercial instrument that could be installed in substations of large customer loads, or used as a hand-held clip on instrument. This paper is particularly useful in determining whether the utility or the customer side has a higher contribution to harmonic pollution in a network. Hence, this method would be helpful in settling utility-customer disputes over who is responsible for harmonic pollution. [ABSTRACT FROM AUTHOR]

Artificial neural networks (ANNs) are a powerful and widely used pattern recognition technique. However, they remain "black boxes" giving no explanation for the decisions they make. This paper presents a new algorithm for extracting a logistic model tree (LMT) from a neural network, which gives a symbolic representation of the knowledge hidden within the ANN. Landwehr's LMTs are based on standard decision trees, but the terminal nodes are replaced with logistic regression functions. This paper reports the results of an empirical evaluation that compares the new decision tree extraction algorithm with Quinlan's C4.5 and ExTree. The evaluation used 12 standard benchmark datasets from the University of California, Irvine machine-learning repository. The results of this evaluation demonstrate that the new algorithm produces decision trees that have higher accuracy and higher fidelity than decision trees created by both C4.5 and ExTree. [ABSTRACT FROM AUTHOR]

This paper introduces a general framework for describing dynamic neural networks—the layered digital dynamic network (LDDN). This framework allows the development of two general algorithms for computing the gradients and Jacobians for these dynamic networks: backpropagation-through-time (BPTT) and real-time recurrent learning (RTRL). The structure of the LDDN framework enables an efficient implementation of both algorithms for arbitrary dynamic networks. This paper demonstrates that the BPTT algorithm is more efficient for gradient calculations, but the RTRL algorithm is more efficient for Jacobian calculations. [ABSTRACT FROM AUTHOR]

Original Hebbian encoding scheme of bidirectional associative memory (BAM) provides a poor pattern capacity and recall performance. Based on Rosenblatt's perceptron learning algorithm, the pattern capacity of BAM is enlarged, and perfect recall of all training pattern pairs is guaranteed. However, these methods put their emphases on pattern capacity, rather than error correction capability which is another critical point of BAM. This paper analyzes the sensitivity to noise in RAM and obtains an interesting idea to improve noise immunity of BAM. Some researchers have found that the noise sensitivity of BAM relates to the minimum absolute value of net inputs (MAV). However, in this paper, the analysis on failure association shows that it is related not only to MAV but also to the variance of weights associated with synapse connections. In fact, it is a positive monotone increasing function of the quotient of MAV divided by the variance of weights. This idea provides an useful principle of improving error correction capability of RAM. Some revised encoding schemes, such as small variance learning for RAM (SVBAM), evolutionary pseudorelaxation learning for BAM (EPRLAB) and evolutionary bidirectional learning (EBL), have been introduced to illustrate the performance of this principle. All these methods perform better than their original versions in noise immunity. Moreover, these methods have no negative effect on the pattern capacity of BAM. The convergence of these methods is also discussed in this paper. If there exist solutions, EPRLAB and EBL always converge to a global optimal solution in the senses of both, pattern capacity and noise immunity. However, the convergence of SVBAM may be affected by a preset function. [ABSTRACT FROM AUTHOR]

This paper presents a new sequential learning algorithm for radial basis function (RBF) networks referred to as generalized growing and pruning algorithm for RBF (GGAP-RBF). The paper first introduces the concept of significance for the hidden neurons and then uses it in the learning algorithm to realize parsimonious networks. The growing and pruning strategy of GGAP-RBF is based on linking the required learning accuracy with the significance of the nearest or intentionally added new neuron. Significance of a neuron is a measure of the average information content of that neuron. The GGAP-RBF algorithm can be used for any arbitrary sampling density for training samples and is derived from a rigorous statistical point of view. Simulation re- suits for bench mark problems in the function approximation area show that the GGAP-RBF outperforms several other sequential learning algorithms in terms of learning speed, network size and generalization performance regardless of the sampling density function of the training data. [ABSTRACT FROM AUTHOR]

With the aim of getting understandable symbolic rules to explain a given phenomenon, we split the task of learning these rules from sensory data in two phases: a multilayer perceptron maps features into propositional variables and a set of subsequent layers operated by a PAC-like algorithm learns Boolean expressions on these variables. The special features of this procedure are that: i) the neural network is trained to produce a Boolean output having the principal task of discriminating between classes of inputs; ii) the symbolic part is directed to compute rules within a family that is not known a priori; iii) the welding point between the two learning systems is represented by a feedback based on a suitability evaluation of the computed rules. The procedure we propose is based on a computational learning paradigm set up recently in some papers in the fields of theoretical computer science, artificial intelligence and cognitive systems. The present article focuses on information management aspects of the procedure. We deal with the lack of prior information about the rules through learning strategies that affect both the meaning of the variables and the description length of the rules into which they combine. The paper uses the task of learning to formally discriminate among several emotional states as both a working example and a test bench for a comparison with previous symbolic and subsymbolic methods in the field. [ABSTRACT FROM AUTHOR]

Classification of power-quality (PQ)-related voltage and current waveform disturbances is a key task for power system monitoring. A new method based on the optimized time-frequency representation (TFR) has been proposed in the first paper [1] of this two-paper series. This paper (the second paper) presents a case study of PQ event classification with the proposed method. The classification algorithm has been successfully tested with $60 real world PQ events that cover five classes, achieving a recognition rate of 98%. The algorithm is implemented on a digital signal processor (DSP) based hardware system and optimized according to the DSP architecture to meet the hard real-time constraints. The DSP-based system is capable of processing a five-cycle (83.3 ms) PQ waveform within 11.2 ms. The real-time computing capability of the algorithm has been verified with this result. The scalability of this method is also discussed. [ABSTRACT FROM AUTHOR]

Under-complete models, which derive lower dimensional representations of input data, are valuable in domains in which the number of input dimensions is very large, such as data consisting of a temporal sequence of images. This paper presents the under-complete product of experts (UPoE), where each expert models a one-dimensional projection of the data. Maximum-likelihood learning rules for this model constitute a tractable and exact algorithm for learning under-complete independent components. The learning rules for this model coincide with approximate learning rules proposed earlier for under-complete independent component analysis (UICA) models. This paper also derives an efficient sequential learning algorithm from this model and discusses its relationship to sequential independent component analysis (ICA), projection pursuit density estimation, and feature induction algorithms for additive random field models. This paper demonstrates the efficacy of these novel algorithms on high-dimensional continuous datasets. [ABSTRACT FROM AUTHOR]

This paper proposes a constructive approach for finding arbitrary (real or complex) roots of arbitrary (real or complex) polynomials by multilayer perceptron network (MLPN) using constrained learning algorithm (CLA), which encodes the a priori information of constraint relations between root moments and coefficients of a polynomial into the usual BP algorithm (BPA). Moreover, the root moment method (RMM) is also simplified into a recursive version so that the computational complexity can be further decreased, which leads the roots of those higher order polynomials to be readily found. In addition, an adaptive learning parameter with the CLA is also proposed in this paper; an initial weight selection method is also given. Finally, several experimental results show that our proposed neural connectionism approaches, with respect to the nonneural ones, are more efficient and feasible in finding the arbitrary roots of arbitrary polynomials. [ABSTRACT FROM AUTHOR]

A fast target maneuver detecting and highly accurate tracking technique using a neural fuzzy network based on Kalman filter is proposed in this paper. In the automatic target tracking system, there exists an important and difficult problem: how to detect the target maneuvers and fast response to avoid miss-tracking? The traditional maneuver detection algorithms, such as variable dimension filter (VDF) and input estimation (IE) etc., are computation intensive and difficult to implement in real time. To solve this problem, neural network algorithms have been issued recently. However, the normal neural networks such as backpropagation networks usually produce the extra problems of low convergence speed and/or large network size. Furthermore, the way to decide the network structure is heuristic. To overcome these defects and to make use of neural learning ability, a developed standard Kalman filter with a self-constructing neural fuzzy inference network (KF-SONFIN) algorithm for target tracking is presented in this paper. By generating possible target trajectories including maneuver information to train the SONFIN, the trained SONFIN can detect when the maneuver occurred, the magnitude of maneuver values and when the maneuver disappeared. Without having to change the structure of Kalman filter nor modeling the maneuvering target, this new algorithm, SONFIN, can always find itself an economic network size with a fast learning process. Simulation results show that the KF-SONFIN is superior to the traditional IE and VDF methods in estimation accuracy. [ABSTRACT FROM AUTHOR]

In this paper, a novel method to make smart recommendations to the user is proposed using Hybrid Broadcast Broadband Television (HbbTV) standard and artificial intelligence. In order to prove this, an HbbTV application is developed to collect real television watching data and a multilayer perceptron model is trained and tested with the collected data to create user profiles. The constructed model is then used to provide recommendations to the users again using the same HbbTV application. Since HbbTV is a widely accepted public consumer electronics standard for digital receivers and most of the recent devices support it, the proposed model is device-agnostic and can reach many people using different consumer devices, which is the main motivation of this study1. [ABSTRACT FROM PUBLISHER]

In recent years, harmonic pollution has worried the power engineers considerably due to the increased penetration of power-electronics-based devices in the utility grid. Monitoring of certain low-order harmonics in the power supply is more important than monitoring of the entire spectrum because, usually, these are the most significant ones. In this paper, a technique based on an adaptive wavelet neural network that is the most suitable for dominant low-order harmonic estimation is presented. The proposed method works with only half-cycle data point inputs, compared to the requirement of at least one-complete-cycle data for other estimation techniques. A simple, fast converging, and reliable learning algorithm based on back propagation is used for training of the network parameters. The proposed method is examined with a number of simulated and experimental signals. The test results confirm that the proposed method accurately estimates the dominant low-order harmonics in pragmatic situations of fundamental frequency deviation, presence of interharmonics, low signal-to-noise ratio, etc. [ABSTRACT FROM PUBLISHER]

The Levenberg–Marquardt (LM) algorithm is a nonlinear parameter learning algorithm that converges accurately and quickly. This paper demonstrates for the first time to our knowledge, a real-time implementation of the LM algorithm on field programmable gate arrays (FPGAs). It was used to train neural networks to solve the eXclusive Or function (XOR), and for 3D-to-2D camera calibration parameter estimation. A Xilinx Virtex-5 ML506 was used to implement the LMA as a hardware-in-the-loop system. The XOR function was approximated in only 13 iterations from zero initial conditions, usually the same function is approximated in thousands of iterations using the error backpropagation algorithm. Also, this type of training not only reduced the number of iterations but also achieved a speed up in excess of 3 \times 10^6 when compared to the software implementation. A real-time camera calibration and parameter estimation was performed successfully on FPGAs. Compared to the software implementation the FPGA implementation led to an increase in the mean squared error and standard deviation by only 17.94% and 8.04% respectively. The FPGA increased the calibration speed by a factor of 1.41 \times 10^6. There are a wide range of systems problems solved via nonlinear parameter optimization, this study demonstrated that a hardware solution for systems such as automated optical inspection systems or systems dealing with projective geometry estimation and motion compensation systems in robotic vision systems is possible in real time. [ABSTRACT FROM PUBLISHER]

In this paper, an application of an adaptive differential evolution (DE) algorithm with multiple trial vectors for training artificial neural networks (ANNs) is presented. The proposed method is \DE-ANNT+, which is a DE-ANN Training (DE-ANNT) modified by adding a multiple trial vectors technique. \DE-ANNT+ allows one to train an ANN of arbitrary architectures, and it offers a nondifferentiable neuron activation function. In contrast to a basic DE algorithm, \DE-ANNT+ possesses two modifications. In \DE-ANNT+, adaptive selection of control parameters and a multiple trial vectors technique are introduced. Adaptive selection means that the number of required parameters of the algorithm is decreased. The multiple trial vectors technique increases the probability of generating a better solution because a greater number of temporary solutions is generated around the existing solutions. The \DE-ANNT+ algorithm, with these two modifications, is used for ANN training to classify the parity-p problem. The results from the obtained algorithm have been compared with results from the following algorithms: an evolutionary algorithm, a DE algorithm without multiple trial vectors, gradient training methods, such as error back-propagation, and the Levenberg-Marquardt method. [ABSTRACT FROM PUBLISHER]

The improved computation presented in this paper is aimed to optimize the neural networks learning process using Levenberg-Marquardt (LM) algorithm. Quasi-Hessian matrix and gradient vector are computed directly, without Jacobian matrix multiplication and storage. The memory limitation problem for LM training is solved. Considering the symmetry of quasi-Hessian matrix, only elements in its upper/lower triangular array need to be calculated. Therefore, training speed is improved significantly, not only because of the smaller array stored in memory, but also the reduced operations in quasi-Hessian matrix calculation. The improved memory and time efficiencies are especially true for large sized patterns training. [ABSTRACT FROM AUTHOR]

In this paper, the optimal probabilistic neural network (PNN) is proposed as the core classifier to discriminate between the magnetizing inrush and the internal fault of a power transformer. The particle swarm optimization is used to obtain an optimal smoothing factor of PNN which is a crucial parameter for PNN. An algorithm has been developed around the theme of the conventional differential protection of the transformer. It makes use of the ratio of voltage-to-frequency and amplitude of differential current for the determination of operating condition of the transformer. The performance of the proposed heteroscedastic-type PNN is investigated with the conventional homoscedastic-type PNN, feedforward back propagation (FFBP) neural network, and the conventional harmonic restraint method. To evaluate the developed algorithm, relaying signals for various operating condition of the transformer, including internal and external faults, are obtained by modeling the transformer in PSCAD/EMTDC. The protection algorithm is implemented by using MATLAB. [ABSTRACT FROM AUTHOR]

In a competitive electricity market, price forecasts are important for market participants. However, electricity price is a complex signal due to its nonlinearity, nonstationarity, and time variant behavior. In spite of much research in this area, more accurate and robust price forecast methods are still required. In this paper, a combination of a feature selection technique and cascaded neuro-evolutionary algorithm (CNEA) is proposed for this purpose. The feature selection method is an improved version of the mutual information (MI) technique. The CNEA is composed of cascaded forecasters where each forecaster consists of a neural network (NN) and an evolutionary algorithm (EA). An iterative search procedure is also incorporated in our solution strategy to fine-tune the adjustable parameters of both the MI technique and CNEA. The price forecast accuracy of the proposed method is evaluated by means of real data from the Pennsylvania-New Jersey-Maryland (PJM) and Spanish electricity markets. The method is also compared with some of the most recent price forecast techniques. [ABSTRACT FROM AUTHOR]

The paper addresses the problem of predicting hourly load demand using adaptive artificial neural networks (ANNs). A particle swarm optimization (PSO) algorithm is employed to adjust the network's weights in the training phase of the ANNs. The advantage of using a PSO algorithm over other conventional training algorithms such as the back-propagation (BP) is that potential solutions will be flown through the problem hyperspace with accelerated movement towards the best solution. Thus the training phase should result in obtaining the weights configuration associated with the minimum output error. Data are wavelet transformed during the preprocessing stage and then inserted into the neural network to extract redundant information from the load curve. This results in better load characterization which creates a more reliable forecasting model. The transformed data of historical load and weather information were trained and tested over various periods of time. The generalized error estimation is done by using the reverse part of the data as a "test" set. The results were compared with traditional BP algorithm and offered a high forecasting precision. [ABSTRACT FROM AUTHOR]

This paper describes a new algorithm with neuron-by-neuron computation methods for the gradient vector and the Jacobian matrix. The algorithm can handle networks with arbitrarily connected neurons. The training speed is comparable with the Levenberg-Marquardt algorithm, which is currently considered by many as the fastest algorithm for neural network training. More importantly, it is shown that the computation of the Jacobian, which is required for second-order algorithms, has a similar computation complexity as the computation of the gradient for first-order learning methods. This new algorithm is implemented in the newly developed software, Neural Network Trainer, which has unique capabilities of handling arbitrarily connected networks. These networks with connections across layers can be more efficient than commonly used multilayer perceptron networks. [ABSTRACT FROM AUTHOR]

In this paper, a new algorithm is proposed for resolution enhancement in hyperspectral images (HSIs). The key techniques are included: spectral unmixing and superresolution mapping, by which spatial and spectral information of HSIs is substantially fused. The proposed algorithm first represents each pixel in scene as a linear combination of landcover spectra and noise. Then, a fully constrained least squares algorithm is used to obtain the proportion of each landcover in each pixel, i.e., abundance, subjecting to two constraints: nonnegativity and sum-to-one. After that, superresolution mapping is performed on high-resolution grids according to spectral unmixing abundances of each landcover and following spatial correlation of clutters. Thus, by reasonably integrating spatial and spectral information of landcovers in HSIs, the proposed algorithm realizes resolution enhancement of the HSIs based on a back-propagation neural network. The proposed algorithm is independent from the a priori information associated with original HSIs, i.e., a main merit of the algorithm. In order to evaluate the performance of the new algorithm, numerical experiments are conducted on both simulated images and real HSIs collected by the Airborne Visible/Infrared Imaging Spectrometer. The proposed algorithm is compared with the traditional method in the experiments. The experimental results prove that the proposed algorithm effectively enhances the resolution of HSIs and indicate its applicability. [ABSTRACT FROM AUTHOR]

The application of neural networks to solve a problem involves tasks with a high computational cost until a suitable network is found, and these tasks mainly involve the selection of the network topology and the training step. We usually select the network structure by means of a trial-and-error procedure, and we then train the network. In the case of recurrent neural networks (RNNs), the lack of suitable training algorithms sometimes hampers these procedures due to vanishing gradient problems. This paper addresses the simultaneous training and topology optimization of RNNs using multiobjective hybrid procedures. The proposal is based on the SPEA2 and NSGA2 algorithms for making hybrid methods using the Baldwinian hybridization strategy. We also study the effects of the selection of the objectives, crossover, and mutation in the diversity during evolution. The proposals are tested in the experimental section to train and optimize the networks in the competition on artificial time-series (CATS) benchmark. [ABSTRACT FROM AUTHOR]

In this paper, we analyze a model of recurrent kernel associative memory (RKAM) recently proposed by Garcia and Moreno. We show that this model consists in a kernelization of the recurrent correlation associative memory (RCAM) of Chiueh and Goodman. In particular, using an exponential kernel, we obtain a generalization of the well-known exponential correlation associative memory (ECAM), while using a polynomial kernel, we obtain a generalization of higher order Hopfield networks with Hebbian weights. We show that the RKAM can outperform the aforementioned associative memory models, becoming equivalent to them when a dominance condition is fulfilled by the kernel matrix. To ascertain the dominance condition, we propose a statistical measure which can be easily computed from the probability distribution of the interpattern Hamming distance or directly estimated from the memory vectors. The RKAM can be used below saturation to realize associative memories with reduced dynamic range with respect to the ECAM and with reduced number of synaptic coefficients with respect to higher order Hopfield networks. [ABSTRACT FROM AUTHOR]

In this paper, we present a recursive algorithm for extracting classification rules from feedforward neural networks (NNs) that have been trained on data sets having both discrete and continuous attributes. The novelty of this algorithm lies in the conditions of the extracted rules: the rule conditions involving discrete attributes are disjoint from those involving continuous attributes. The algorithm starts by first generating rules with discrete attributes only to explain the classification process of the NN. If the accuracy of a rule with only discrete attributes is not satisfactory, the algorithm refines this rule by recursively generating more rules with discrete attributes not already present in the rule condition, or by generating a hyperplane involving only the continuous attributes. We show that for three real-life credit scoring data sets, the algorithm generates rules that are not only more accurate but also more comprehensible than those generated by other NN rule extraction methods. [ABSTRACT FROM AUTHOR]

The hierarchical graph neuron (HGN) implements a single cycle memorization and recall operation through a novel algorithmic design. The HGN is an improvement on the already published original graph neuron (GN) algorithm. In this improved approach, it recognizes incomplete/noisy patterns. It also resolves the crosstalk problem, which is identified in the previous publications, within closely matched patterns. To accomplish this, the HGN links multiple GN networks for filtering noise and crosstalk out of pattern data inputs. Intrinsically, the HGN is a lightweight in-network processing algorithm which does not require expensive floating point computations; hence, it is very suitable for real-time applications and tiny devices such as the wireless sensor networks. This paper describes that the HGN's pattern matching capability and the small response time remain insensitive to the increases in the number of stored patterns. Moreover, the HGN does not require definition of rules or setting of thresholds by the operator to achieve the desired results nor does it require heuristics entailing iterative operations for memorization and recall of patterns. [ABSTRACT FROM AUTHOR]

Continuum or hyper-redundant robot manipulators can exhibit behavior similar to biological trunks, tentacles, or snakes. Unlike traditional rigid-link robot manipulators, continuum robot manipulators do not have rigid joints, hence these manipulators are extremely dexterous, compliant, and are capable of dynamic adaptive manipulation in unstructured environments. However, the development of high-performance control algorithms for these manipulators is quite a challenge, due to their unique design and the high degree of uncertainty in their dynamic models. In this paper, a controller for continuum robots, which utilizes a neural network feedforward component to compensate for dynamic uncertainties is presented. Experimental results using the OCTARM, which is a soft extensible continuum manipulator, are provided to illustrate that the addition of the neural network feedforward component to the controller provides improved performance. [ABSTRACT FROM AUTHOR]

Robots operating in everyday life environments are often required to switch between different tasks. While learning and evolution have been effectively applied to single task performance, multiple task performance still lacks methods that have been demonstrated to be both reliable and efficient. This paper introduces a new method for multiple task performance based on multiobjective evolutionary algorithms, where each task is considered as a separate objective function. In order to verify the effectiveness, the proposed method is applied to evolve neural controllers for the Cyber Rodent (CR) robot that has to switch properly between two distinctly different tasks: 1) protecting another moving robot by following it closely and 2) collecting objects scattered in the environment. Furthermore, the tasks and neural complexity are analyzed by including the neural structure as a separate objective function. The simulation and experimental results using the CR robot show that the multiobjective-based evolutionary method can be applied effectively for generating neural networks that enable the robot to perform multiple tasks simultaneously. [ABSTRACT FROM AUTHOR]

This paper presents an analysis of a random access memory (RAM)-based associative memory which uses a weighted voting scheme for information retrieval. This weighted voting memory can operate in heteroassociative or autoassociative mode, can store both real-valued and binary-valued patterns and, unlike memory models, is equipped with a rejection mechanism. A theoretical analysis of the performance of the weighted voting memory is given for the case of binary and random memory sets. Performance measures are derived as a function of the model parameters: pattern size, window size, and number of patterns in the memory set. It is shown that the weighted voting model has large capacity and error correction. The results show that the weighted voting model can successfully achieve high-detection and -identification rates and, simultaneously, low-false-acceptance rates. [ABSTRACT FROM AUTHOR]

This paper proposes noisy speech recognition using hierarchical singleton-type recurrent neural fuzzy networks (HSRNFNs). The proposed HSRNFN is a hierarchical connection of two singleton-type recurrent neural fuzzy networks (SRNFNs), where one is used for noise filtering and the other for recognition. The SRNFN is constructed by recurrent fuzzy if-then rules with fuzzy singletons in the consequences, and their recurrent properties make them suitable for processing speech patterns with temporal characteristics. In n words recognition, n SRNFNs are created for modeling n words, where each SRNFN receives the current frame feature and predicts the next one of its modeling word. The prediction error of each SRNFN is used as recognition criterion. In filtering, one SRNFN is created, and each SRNFN recognizer is connected to the same SRNFN filter, which filters noisy speech patterns in the feature domain before feeding them to the SRNFN recognizer. Experiments with Mandarin word recognition under different types of noise are performed. Other recognizers, including multilayer perceptron (MLP), time-delay neural networks (TDNNs), and hidden Markov models (HMMs), are also tested and compared. These experiments and comparisons demonstrate good results with HSRNFN for noisy speech recognition tasks. [ABSTRACT FROM AUTHOR]

This paper proposes unconstrained functional networks as a new classifier to deal with the pattern recognition problems. Both methodology and learning algorithm for this kind of computational intelligence classifier using the iterative least squares optimization criterion are derived. The performance of this new intelligent systems scheme is demonstrated and examined using real-world applications. A comparative study with the most common classification algorithms in both machine learning and statistics communities is carried out. The study was achieved with only sets of second-order linearly independent polynomial functions to approximate the neuron functions. The results show that this new framework classifier is reliable, flexible, stable, and achieves a high-quality performance. [ABSTRACT FROM AUTHOR]

In this paper, we present an incremental method for model selection and learning of Gaussian mixtures based on the recently proposed variational Bayes approach. The method adds components to the mixture using a Bayesian splitting test procedure: a component is split into two components and then variational update equations are applied only to the parameters of the two components. As a result, either both components are retained in the model or one of them is found to be redundant and is eliminated from the model. In our approach, the model selection problem is treated locally, in a region of the data space, so we can set more informative priors based on the local data distribution. A modified Bayesian mixture model is presented to implement this approach, along with a learning algorithm that iteratively applies a splitting test on each mixture component. Experimental results and comparisons with two other techniques testify for the adequacy of the proposed approach. [ABSTRACT FROM AUTHOR]

In this paper, a novel exemplar-based constructive approach using kernels is proposed for simultaneous pattern classification and multidomain pattern association tasks. The kernel networks are constructed on a modular basis by a simple one-shot self-structuring algorithm motivated from the traditional Hebbian principle and then, they act as the flexible memory capable of generalization for the respective classes. In the self-structuring kernel memory (SSKM), any arduous and iterative network parameter tuning is not involved for establishing the weight connections during the construction, unlike conventional approaches, and thereby, it is considered that the networks do not inherently suffer from the associated numerical instability. Then, the approach is extended for multidomain pattern association, in which a particular domain input cannot only activate some kernel units (KUs) but also the kernels in other domain(s) via the cross-domain connection(s) in between. Thereby, the SSKM can be regarded as a simultaneous pattern classifier and associator. In the simulation study for pattern classification, it is justified that an SSKM consisting of distinct kernel networks can yield relatively compact-sized pattern classifiers, while preserving a reasonably high generalization capability, in comparison with the approach using support vector machines (SVMs). [ABSTRACT FROM AUTHOR]

In this paper, we present two fast sparse approximation schemes for least squares support vector machine (LS-SVM), named FSALS-SVM and PFSALS-SVM, to overcome the limitation of LS-SVM that it is not applicable to large data sets and to improve test speed. FSALS-SVM iteratively builds the decision function by adding one basis function from a kernel-based dictionary at one time. The process is terminated by using a flexible and stable epsilon insensitive stopping criterion. A probabilistic speedup scheme is employed to further improve the speed of FSALS-SVM and the resulting classifier is named PFSALS-SVM. Our algorithms are of two compelling features: low complexity and sparse solution. Experiments on benchmark data sets show that our algorithms obtain sparse classifiers at a rather low cost without sacrificing the generalization performance. [ABSTRACT FROM AUTHOR]