PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Neural Networks, Computer”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,387 records · Page 77Linked to original sources
PubMed1996

Stimulus-response diversity in local neuronal populations of the cerebral cortex.

In cortex, neighboring 0.05 mm minicolumns have distinctly different receptive fields (RFs). Within minicolumns, neighboring cells have very similar RFs, but differ prominently in their stimulus-evoked temporal behaviors. This is reproduced in a cortical model that has strong inhibition and semi-random lateral connections among cells with similar RFs. Within modeled minicolumns, non-linear dynamics amplify small differences in cells' lateral inputs into large differences in temporal behaviors. Cells' stimulus-evoked behaviors, though complex, are surprisingly orderly, in that (1) time courses of cells' responses are very stimulus-specific and (2) in the presence of a stimulus, activities of some cells fluctuate coherently, and the patterns of coherence are also stimulus-specific. Thus the model, like real cortex, represents stimulus information in the overall strengths and temporal patterns of cells' responses and in patterns of temporal coherence among cells.

Cerebral Cortex↗
PubMed2004

Reassessment of catastrophic interference.

Connectionist models using the back propagation learning rule are known to have a serious problem in that they exhibit catastrophic interference (or forgetting) with sequential training. After the model learns the first set of patterns, if the model is trained on another set of patterns, its performance on the first set dramatically deteriorates very rapidly. The present study reconsiders this issue with three sets of simulations. With orthogonal input vectors, interference can be reasonably mild. The number of hidden units was critical for the degree of interference, in contrast to suggestions of previous studies. Output coding scheme was found to be critical. The length of input lists also influenced the degree of interference. This study suggests that the interference problem has been overstated in the literature.

Computer Simulation↗
PubMed2004

Fusing images with different focuses using support vector machines.

Many vision-related processing tasks, such as edge detection, image segmentation and stereo matching, can be performed more easily when all objects in the scene are in good focus. However, in practice, this may not be always feasible as optical lenses, especially those with long focal lengths, only have a limited depth of field. One common approach to recover an everywhere-in-focus image is to use wavelet-based image fusion. First, several source images with different focuses of the same scene are taken and processed with the discrete wavelet transform (DWT). Among these wavelet decompositions, the wavelet coefficient with the largest magnitude is selected at each pixel location. Finally, the fused image can be recovered by performing the inverse DWT. In this paper, we improve this fusion procedure by applying the discrete wavelet frame transform (DWFT) and the support vector machines (SVM). Unlike DWT, DWFT yields a translation-invariant signal representation. Using features extracted from the DWFT coefficients, a SVM is trained to select the source image that has the best focus at each pixel location, and the corresponding DWFT coefficients are then incorporated into the composite wavelet representation. Experimental results show that the proposed method outperforms the traditional approach both visually and quantitatively.

Algorithms↗
PubMed2004

The pre-image problem in kernel methods.

In this paper, we address the problem of finding the pre-image of a feature vector in the feature space induced by a kernel. This is of central importance in some kernel applications, such as on using kernel principal component analysis (PCA) for image denoising. Unlike the traditional method which relies on nonlinear optimization, our proposed method directly finds the location of the pre-image based on distance constraints in the feature space. It is noniterative, involves only linear algebra and does not suffer from numerical instability or local minimum problems. Evaluations on performing kernel PCA and kernel clustering on the USPS data set show much improved performance.

Algorithms↗
PubMed2005

Recognizing partially occluded, expression variant faces from single training image per person with SOM and soft kappa-NN ensemble.

Most classical template-based frontal face recognition techniques assume that multiple images per person are available for training, while in many real-world applications only one training image per person is available and the test images may be partially occluded or may vary in expressions. This paper addresses those problems by extending a previous local probabilistic approach presented by Martinez, using the self-organizing map (SOM) instead of a mixture of Gaussians to learn the subspace that represented each individual. Based on the localization of the training images, two strategies of learning the SOM topological space are proposed, namely to train a single SOM map for all the samples and to train a separate SOM map for each class, respectively. A soft kappa nearest neighbor (soft kappa-NN) ensemble method, which can effectively exploit the outputs of the SOM topological space, is also proposed to identify the unlabeled subjects. Experiments show that the proposed method exhibits high robust performance against the partial occlusions and variant expressions.

Algorithms↗
PubMed2005

Sensitivity to noise in bidirectional associative memory (BAM).

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 BAM 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 BAM. Some revised encoding schemes, such as small variance learning for BAM (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.

Algorithms↗
PubMed2005

Crossover enhancements in GEFREX.

This letter describes some improvements to the crossover operator in the genetic-neuro-fuzzy algorithm called genetic fuzzy rule extractor (GEFREX). Although, the new crossovers studied are very simple the performance of GEFREX, in terms of learning time, is decidedly improved.

Algorithms↗
PubMed2006

A geometric approach to support vector machine (SVM) classification.

The geometric framework for the support vector machine (SVM) classification problem provides an intuitive ground for the understanding and the application of geometric optimization algorithms, leading to practical solutions of real world classification problems. In this work, the notion of "reduced convex hull" is employed and supported by a set of new theoretical results. These results allow existing geometric algorithms to be directly and practically applied to solve not only separable, but also nonseparable classification problems both accurately and efficiently. As a practical application of the new theoretical results, a known geometric algorithm has been employed and transformed accordingly to solve nonseparable problems successfully.

Algorithms↗
PubMed2006

Monitoring the formation of kernel-based topographic maps in a hybrid SOM-kMER model.

A new lattice disentangling monitoring algorithm for a hybrid self-organizing map-kernel-based maximum entropy learning rule (SOM-kMER) model is proposed. It aims to overcome topological defects owing to a rapid decrease of the neighborhood range over the finite running time in topographic map formation. The empirical results demonstrate that the proposed approach is able to accelerate the formation of a topographic map and, at the same time, to simplify the monitoring procedure.

Algorithms↗
PubMed2006

Multiuser receiver for DS-CDMA signals in multipath channels: an enhanced multisurface method.

This paper deals with the problem of multiuser detection in direct-sequence code-division multiple-access (DS-CDMA) systems in multipath environments. The existing multiuser detectors can be divided into two categories: (1) low-complexity poor-performance linear detectors and (2) high-complexity good-performance nonlinear detectors. In particular, in channels where the orthogonality of the code sequences is destroyed by multipath, detectors with linear complexity perform much worse than the nonlinear detectors. In this paper, we propose an enhanced multisurface method (EMSM) for multiuser detection in multipath channels. EMSM is an intermediate piecewise linear detection scheme with a run-time complexity linear in the number of users. Its bit error rate performance is compared with existing linear detectors, a nonlinear radial basis function detector trained by the new support vector learning algorithm, and Verdu's optimal detector. Simulations in multipath channels, for both synchronous and asynchronous cases, indicate that it always outperforms all other linear detectors, performing nearly as well as nonlinear detectors.

Algorithms↗
PubMed2006

Evolving compact and interpretable Takagi-Sugeno fuzzy models with a new encoding scheme.

Developing Takagi-Sugeno fuzzy models by evolutionary algorithms mainly requires three factors: an encoding scheme, an evaluation method, and appropriate evolutionary operations. At the same time, these three factors should be designed so that they can consider three important aspects of fuzzy modeling: modeling accuracy, compactness, and interpretability. This paper proposes a new evolutionary algorithm that fulfills such requirements and solves fuzzy modeling problems. Two major ideas proposed in this paper lie in a new encoding scheme and a new fitness function, respectively. The proposed encoding scheme consists of three chromosomes, one of which uses unique chained possibilistic representation of rule structure. The proposed encoding scheme can achieve simultaneous optimization of parameters of antecedent membership functions and rule structures with the new fitness function developed in this paper. The proposed fitness function consists of five functions that consider three evaluation criteria in fuzzy modeling problems. The proposed fitness function guides evolutionary search direction so that the proposed algorithm can find more accurate compact fuzzy models with interpretable antecedent membership functions. Several evolutionary operators that are appropriate for the proposed encoding scheme are carefully designed. Simulation results on three modeling problems show that the proposed encoding scheme and the proposed fitness functions are effective in finding accurate, compact, and interpretable Takagi-Sugeno fuzzy models. From the simulation results, it is shown that the proposed algorithm can successfully find fuzzy models that approximate the given unknown function accurately with a compact number of fuzzy rules and membership functions. At the same time, the fuzzy models use interpretable antecedent membership functions, which are helpful in understanding the underlying behavior of the obtained fuzzy models.

Algorithms↗
PubMed2005

Reduced basal activity and increased functional homogeneity in sensorimotor and striatum of a Parkinson's disease rat model: a functional MRI study.

Functional neuro-imaging studies of Parkinson's disease (PD) patients and animal models show inconsistent cortical responses to sensory stimulation: some present increased sensorimotor cortex activation contradicting classical basal ganglia-cortex circuitry models, whereas others show decreased activation. As functional neuro-imaging activation is defined as the signal difference between stimulation ON and stimulation OFF, reduced 'activation' can point to either increased neuronal activity during stimulation ON or to decreased basal neuronal activity during stimulation OFF. A unique non-invasive method that uses the temporal and the spatial variances of functional magnetic resonance imaging signal is employed here to compare basal neuronal activity levels and 'functional homogeneity' between groups. Based on the assumption that the temporal variance reflects average neuronal activity, the variance of activity within a predefined region is defined as the region's 'functional homogeneity', which is assumed to estimate neuronal synchronization. Comparison of temporal and spatial variances of the sensorimotor cortex and the striatum in the 6-hydroxydopamine (6-OHDA) PD rat model and a control rat group show bilaterally decreased temporal and spatial variances in the 6-OHDA rat group, suggesting bilateral reduction of basal neuronal activity levels together with an increase in local neuronal synchronization in line with classical basal ganglia-cortex circuit models.

Adrenergic Agents↗
PubMed2000

Simulink-based HW/SW codesign of embedded neuro-fuzzy systems.

We propose a semi-automatic HW/SW codesign flow for low-power and low-cost Neuro-Fuzzy embedded systems. Applications range from fast prototyping of embedded systems to high-speed simulation of Simulink models and rapid design of Neuro-Fuzzy devices. The proposed codesign flow works with different technologies and architectures (namely, software, digital and analog). We have used The Mathworks' Simulink environment for functional specification and for analysis of performance criteria such as timing (latency and throughput), power dissipation, size and cost. The proposed flow can exploit trade-offs between SW and HW as well as between digital and analog implementations, and it can generate, respectively, the C, VHDL and SKILL codes of the selected architectures.

Analog-Digital Conversion↗
PubMed2003

An efficient approach to the travelling salesman problem using self-organizing maps.

This paper presents an approach to the well-known Travelling Salesman Problem (TSP) using Self-Organizing Maps (SOM). The SOM algorithm has interesting topological information about its neurons configuration on cartesian space, which can be used to solve optimization problems. Aspects of initialization, parameters adaptation, and complexity analysis of the proposed SOM based algorithm are discussed. The results show an average deviation of 3.7% from the optimal tour length for a set of 12 TSP instances.

Algorithms↗
PubMed2003

Cost component analysis.

In optimizations the dimension of the problem may severely, sometimes exponentially increase optimization time. Parametric function approximatiors (FAPPs) have been suggested to overcome this problem. Here, a novel FAPP, cost component analysis (CCA) is described. In CCA, the search space is resampled according to the Boltzmann distribution generated by the energy landscape. That is, CCA converts the optimization problem to density estimation. Structure of the induced density is searched by independent component analysis (ICA). The advantage of CCA is that each independent ICA component can be optimized separately. In turn, (i) CCA intends to partition the original problem into subproblems and (ii) separating (partitioning) the original optimization problem into subproblems may serve interpretation. Most importantly, (iii) CCA may give rise to high gains in optimization time. Numerical simulations illustrate the working of the algorithm.

Algorithms↗
PubMed2004

Design of general bidirectional associative memories with improved recall capability.

The concept of qth order Hamming ball for general bidirectional associative memories (GBAMs) is presented, which results in an enhanced recall capability. A technique based on the minimum overlap algorithm (MOA) is proposed to deal with the separability problem of the qth order Hamming balls. Simulation results show that the recall capability obtained by using the proposed method is indeed larger than that obtained by using the conventional method.

Algorithms↗