Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Neural network”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

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

At least 1,117 records · Page 62Linked to original sources
PubMed2001

Application of artificial neural networks to the classification of soils from São Paulo State using near-infrared spectroscopy.

This paper describes how artificial neural networks can be used to classify multivariate data. Two types of neural networks were applied: a counter propagation neural network (CP-ANN) and a radial basis function network (RBFN). These strategies were used to classify soil samples from different geographical regions in Brazil by means of their near-infrared (diffuse reflectance) spectra. The results were better with CP-ANN (classification error 8.6%) than with RBFN (classification error 11.0%).

Journal Article↗
PubMed1998

A neural network study of precollicular saccadic averaging.

Saccadic averaging is the phenomenon that two simultaneously presented retinal inputs result in a saccade with an endpoint located on an intermediate position between the two stimuli. Recordings from neurons in the deeper layers of the superior colliculus have revealed neural correlates of saccade averaging, indicating that it takes place at this level or upstream. Recently, we proposed a neural network for internal feedback in saccades. This neural network model is different from other models in that it suggests the possibility that averaging takes place in a stage upstream of the colliculus. The network consists of output units representing the neural map of the deeper layers of the superior colliculus and hidden layers imitating areas in the posterior parietal cortex. The deeper layers of the superior colliculus represent the motor error of a desired saccade, e.g. an eye movement to a visual target. In this article we show that averaging is an emergent property of the proposed network. When two retinal targets with different intensities are simultaneously presented to the network, the activity in the output layer represents a single motor error with a weighted average value. Our goal is to understand the mechanism of weighted averaging in this neural network. It appears that averaging in the model is caused by the linear dependence of the net input, received by the hidden units, on retinal error, independent of its retinal coding format. For nonnormalized retinal error inputs, also the nonlinearity between the net input and the activity of the hidden units plays a role in the averaging process. The averaging properties of the model are in agreement with physiological experiments if the hypothetical retinal error input map is normalized. The neural network predicts that if this normalization is overruled by electrical stimulation, averaging still takes place. However, in this case--as a consequence of the feedback task--the location of the resulting saccade depends on the initial eye position and the total intensity/current applied at the two locations. This could be a way to verify the neural network model. If the assumptions for the model are valid, a physiological implication of this paper is that averaging of saccades takes place upstream of the superior colliculus.

Animals↗
PubMed2002

Neural networks--a diagnostic tool in acute myocardial infarction with concomitant left bundle branch block.

The prognosis of acute myocardial infarction (AMI) improves by early revascularization. However the presence of left bundle branch block (LBBB) in the electrocardiogram (ECG) increases the difficulty in recognizing an AMI and different ECG criteria for the diagnosis of AMI have proved to be of limited value. The purpose of this study was to detect AMI in ECGs with LBBB using artificial neural networks and to compare the performance of the networks to that of six sets of conventional ECG criteria and two experienced cardiologists. A total of 518 ECGs, recorded at an emergency department, with a QRS duration > 120 ms and an LBBB configuration, were selected from the clinical ECG database. Of this sample 120 ECGs were recorded on patients with AMI, the remaining 398 ECGs being used as a control group. Artificial neural networks of feed-forward type were trained to classify the ECGs as AMI or not AMI. The neural network showed higher sensitivities than both the cardiologists and the criteria when compared at the same levels of specificity. The sensitivity of the neural network was 12% (P = 0.02) and 19% (P = 0.001) higher than that of the cardiologists. Artificial neural networks can be trained to detect AMI in ECGs with concomitant LBBB more effectively than conventional ECG criteria or experienced cardiologists.

Acute Disease↗
PubMed1999

A neural network approach to the diagnosis of morbidity outcomes in trauma care.

This paper introduces the application of artificial neural networks to trauma complications assessment. The potential financial benefits of improving on trauma center diagnostic specificity in complications assessment are illustrated and the operational feasibility of the use of diagnostic neural models across institutions is discussed. A prototype neural network model is described, which, after training, succeeds in diagnosing the complication of sepsis in victims of traumatic blunt injury. Its diagnostic performance with 100% sensitivity and 96.5% specificity is accomplished with test data from a regional trauma center. The model is further shown to have correctly detected, during training, incorrectly coded data. The potential this suggests, for parsimonious database scrubbing through the use of neural network models, is discussed.

Computer Simulation↗
PubMed2002

A comparative study on kernel-based probabilistic neural networks for speaker verification.

This paper compares kernel-based probabilistic neural networks for speaker verification based on 138 speakers of the YOHO corpus. Experimental evaluations using probabilistic decision-based neural networks (PDBNNs), Gaussian mixture models (GMMs) and elliptical basis function networks (EBFNs) as speaker models were conducted. The original training algorithm of PDBNNs was also modified to make PDBNNs appropriate for speaker verification. Results show that the equal error rate obtained by PDBNNs and GMMs is less than that of EBFNs (0.33% vs. 0.48%), suggesting that GMM- and PDBNN-based speaker models outperform the EBFN ones. This work also finds that the globally supervised learning of PDBNNs is able to find decision thresholds that not only maintain the false acceptance rates to a low level but also reduce their variation, whereas the ad-hoc threshold-determination approach used by the EBFNs and GMMs causes a large variation in the error rates. This property makes the performance of PDBNN-based systems more predictable.

Algorithms↗
PubMed2004

Wavelet-based neural network analysis of ophthalmic artery Doppler signals.

In this study, ophthalmic artery Doppler signals were recorded from 115 subjects, 52 of whom had ophthalmic artery stenosis while the rest were healthy controls. Results were classified using a wavelet-based neural network. The wavelet-based neural network model, employing the multilayer perceptron, was used for analysis of ophthalmic artery Doppler signals. A multilayer perceptron neural network (MLPNN) trained with the Levenberg-Marquardt algorithm was used to detect stenosis in ophthalmic arteries. In order to determine the MLPNN inputs, spectral analysis of ophthalmic artery Doppler signals was performed using wavelet transform. The MLPNN was trained, cross validated, and tested with training, cross validation, and testing sets, respectively. All data sets were obtained from ophthalmic arteries of healthy subjects and subjects suffering from ophthalmic artery stenosis. The correct classification rate was 97.22% for healthy subjects, and 96.77% for subjects having ophthalmic artery stenosis. The classification results showed that the MLPNN trained with the Levenberg-Marquardt algorithm was effective to detect ophthalmic artery stenosis.

Adult↗
PubMed1994

Directional operations in the motor cortex modeled by a neural network of spiking neurons.

A neural network with realistically modeled, spiking neurons is proposed to model ensemble operations of directionally tuned neurons in the motor cortex. The model reproduces well directional operations previously identified experimentally, including the prediction of the direction of an upcoming movement in reaching tasks and the rotation of the neuronal population vector in a directional transformation task.

Action Potentials↗
PubMed1997

An Efficient Method to Construct a Radial Basis Function Neural Network Classifier.

Radial basis function neural network (RBFN) has the power of the universal function approximation. But how to construct an RBFN to solve a given problem is usually not straightforward. This paper describes a method to construct an RBFN classifier efficiently and effectively. The method determines the middle layer neurons by a fast clustering algorithm and computes the optimal weights between the middle and the output layers statistically. We applied the proposed method to construct an RBFN classifier for an unconstrained handwritten digit recognition. The experiment showed that the method could construct an RBFN classifier quickly and the performance of the classifier was better than the best result previously reported.

Journal Article↗
PubMed1998

Robust maximum likelihood training of heteroscedastic probabilistic neural networks.

We consider the probabilistic neural network (PNN) that is a mixture of Gaussian basis functions having different variances. Such a Gaussian heteroscedastic PNN is more economic, in terms of the number of kernel functions required, than the Gaussian mixture PNN of a common variance. The expectation-maximisation (EM) algorithm, although a powerful technique for constructing maximum likelihood (ML) homoscedastic PNNs, often encounters numerical difficulties when training heteroscedastic PNNs. We combine a robust statistical technique known as the Jack-knife with the EM algorithm to provide a robust ML training algorithm. An artificial-data case, the two-dimensional XOR problem, and a real-data case, success or failure prediction of UK private construction companies, are used to evaluate the performance of this robust learning algorithm.

Journal Article↗
PubMed1998

Inhibitory connections in the assembly neural network for texture segmentation.

A neural network with assembly organization is described. This assembly network is applied to the problem of texture segmentation in natural scenes. The network is partitioned into several subnetworks: one for each texture class. Hebb's assemblies are formed in the subnetworks during the process of training the excitatory connections. Also, a structure of the inhibitory connections is formed in the assembly network during a separate training process. The inhibitory connections result in inhibitory interactions between different subnetworks. Computer simulation of the network has been performed. Experiments show that an adequately trained assembly network with inhibitory connections is more efficient than without them.

Journal Article↗
PubMed1988

Differentiating the effects of three benzodiazepines on non-REM sleep EEG spectra. A neural-network pattern classification analysis.

Neural-network pattern classifiers were used to study the effects of long half-life flurazepam (30 mg) and quazepam (15 mg), and short half-life triazolam (0.5 mg) on non-REM sleep. We measured the magnitude of effect, time course, and EEG spectral signature of the three benzodiazepines as a function of third-of-night. Of the three benzodiazepines studied, flurazepam had the largest effect and quazepam had the most stable time course. The effects of triazolam were similar to those of quazepam. These EEG differences may prove to be more clinically useful markers than the usual measurement of plasma levels, and may be used to guide the therapy of sleep disorders.

Adult↗
PubMed2002

Optical finite impulse response neural networks.

The finite impulse response neural network is described in detail. Different algorithms capable of temporal back-propagation are considered, including a novel modification to the conventional algorithm, called the delayed-feedback back-propagation algorithm. We present and analyze different optoelectronic processors making use of adaptive volume holograms and three-dimensional optical processing. Two single-layer architectures are presented: the input delay plane architecture and the output delay plane architecture. By combining them it is possible to implement both forward and backward propagation in two multi-layer architectures: the first making use of the conventional temporal back-propagation and the second making use of delayed-feedback back-propagation.

Journal Article↗
PubMed2004

Programmable optoelectronic neural network for optimization.

An optoelectronic neural network is presented that is designed to solve the assignment problem--or any similar optimization task given minimal adjustment--in both crossbar and banyan packet switches. We examine the design decisions made at the hardware, software, and algorithmic levels and indicate the associated effect on the system as a whole. Clearly detailed experimental results show the system's robustness and performance due to the particular optoelectronic-algorithm combination used. The integration and packaging of such a system are also briefly discussed.

Journal Article↗
PubMed2005

[Spectrophotometric simultaneous determination of pyrocatechol, resorcinol and hydroquinone by LM-BP neural network].

By means of artificial neural network and Levenberg Marquardt Back Propagation (LM-BP) train algorithm, the three components of pyrocatechol, resorcinol and hydroquinone were determined simultaneously. The absorption spectra of these three components severely overlap in ultraviolet spectral range. Three wavelengths at 283.5, 279.5 and 276.5 nm were selected for the determination. 25 mixture standard solutions were prepared according to orthogonal projection form L25 (5(6)). Three kinds of components were trained. Mean Squared Error (MSE) reaching minimum value is 0.083 114 3. Meanwhile the contents of pyrocatechol, resorcinol and hydroquinone in six simulation mixture samples were predicted. The relative errors of the three kinds of components were slightly larger under the low concentration condition, and the mean relative error for most analytical results was less than 5%, especially it is satisfactory for the analytical results of pyrocatechol and resorcinol with severely overlapped absorption spectra.

English Abstract↗
PubMed1993

Neural network based classification of single-trial EEG data.

Standard Back Propagation (BP), Partially Recurrent (PR) and Cascade-Correlation (CC) neural networks were used to predict the side of finger movement on the basis of non-averaged single trial multi-channel EEG data recorded prior to movement. From these EEG data, power values were calculated and used as parameters for classification. The results obtained on three subjects show that the Cascade-Correlation neural network is an appropriate choice for neural network based classification of spatio-temporal single-trial EEG patterns. It is fast, stable and able to discover and recognize underlying dynamics of rhythmic activities within the alpha band which precede execution of hand movements.

Algorithms↗
PubMed1989

An investigation of trained neural networks from a neurophysiological perspective.

The application of theoretical neural networks to preprocessed images was investigated with the aim of developing a computational recognition system. The neural networks were trained by means of a back-propagation algorithm, to respond selectively to computer-generated bars and edges. The receptive fields of the trained networks were then mapped, in terms of both their synaptic weights and their responses to spot stimuli. There was a direct relationship between the pattern of weights on the inputs to the hidden units (the units in the intermediate layer between the input and the output units), and their receptive field as mapped by spot stimuli. This relationship was not sustained at the level of the output units in that their spot-mapped responses failed to correspond either with the weights of the connections from the hidden units to the output units, or with a qualitative analysis of the networks. Part of this discrepancy may be ascribed to the output function used in the back-propagation algorithm.

Algorithms↗
PubMed2004

Artificial neural network based soft estimator for estimation of transducer static nonlinearity.

In this work, the development of an Artificial Neural Network (ANN) based soft estimator is reported for the estimation of static-nonlinearity associated with the transducers. Under the realm of ANN based transducer modeling, only two neural models have been suggested to estimate the static-nonlinearity associated with the transducers with quite successful results. The first existing model is based on the concept of a functional link artificial neural network (FLANN) trained with mu-LMS (Least Mean Squares) learning algorithm. The second one is based on the architecture of a single layer linear ANN trained with alpha-LMS learning algorithm. However, both these models suffer from the problem of slow convergence (learning). In order to circumvent this problem, it is proposed to synthesize the direct model of transducers using the concept of a Polynomial-ANN (polynomial artificial neural network) trained with Levenberg-Marquardt (LM) learning algorithm. The proposed Polynomial-ANN oriented transducer model is implemented based on the topology of a single-layer feed-forward back-propagation-ANN. The proposed neural modeling technique provided an extremely fast convergence speed with increased accuracy for the estimation of transducer static nonlinearity. The results of convergence are very stimulating with the LM learning algorithm.

Algorithms↗
PubMed1991

Artificial neural networks for source localization in the human brain.

Source localization in the brain remains an ill-posed problem unless further constraints about the type of sources and the head model are imposed. Human head is modeled in various ways depending critically on the computing power available and/or the required level of accuracy. Sophisticated and truly representative models may yield more accurate results in general, but at the cost of prohibitively long computer times and huge memory requirements. In conventional source localization techniques, solution source parameters are taken as those which minimize an index of performance, defined relative to the model-generated and clinically measured voltages. We propose the use of a neural network in the place of commonly employed minimization algorithms such as the Simplex Method and the Marquardt algorithm, which are iterative and time consuming. With the aid of the error-backpropagation technique, a neural network is trained to compute source parameters, starting from a voltage set measured on the scalp. Here we describe the methods of training the neural network and investigate its localization accuracy. Based on the results of extensive studies, we conclude that neural networks are highly feasible as source localizers. A trained neural network's independence of localization speed from the head model, and the rapid localization ability, makes it possible to employ the most complex head model with the ease of the simplest model. No initial parameters need to be guessed in order to start the calculation, implying a possible automation of the entire localization process. One may train the network on experimental data, if available, thereby possibly doing away with head models.

Brain↗