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 91 records · Page 5Linked to original sources
PubMed2006

Modeling gravity-dependent plasticity of the angular vestibuloocular reflex with a physiologically based neural network.

A neural network model was developed to explain the gravity-dependent properties of gain adaptation of the angular vestibuloocular reflex (aVOR). Gain changes are maximal at the head orientation where the gain is adapted and decrease as the head is tilted away from that position and can be described by the sum of gravity-independent and gravity-dependent components. The adaptation process was modeled by modifying the weights and bias values of a three-dimensional physiologically based neural network of canal-otolith-convergent neurons that drive the aVOR. Model parameters were trained using experimental vertical aVOR gain values. The learning rule aimed to reduce the error between eye velocities obtained from experimental gain values and model output in the position of adaptation. Although the model was trained only at specific head positions, the model predicted the experimental data at all head positions in three dimensions. Altering the relative learning rates of the weights and bias improved the model-data fits. Model predictions in three dimensions compared favorably with those of a double-sinusoid function, which is a fit that minimized the mean square error at every head position and served as the standard by which we compared the model predictions. The model supports the hypothesis that gravity-dependent adaptation of the aVOR is realized in three dimensions by a direct otolith input to canal-otolith neurons, whose canal sensitivities are adapted by the visual-vestibular mismatch. The adaptation is tuned by how the weights from otolith input to the canal-otolith-convergent neurons are adapted for a given head orientation.

Adaptation, Physiological↗
PubMed1997

Emergence of clusters in the hidden layer of a dynamic recurrent neural network.

The neural integrator of the oculomotor system is a privileged field for artificial neural network simulation. In this paper, we were interested in an improvement of the biologically plausible features of the Arnold-Robinson network. This improvement was done by fixing the sign of the connection weights in the network (in order to respect the biological Dale's Law). We also introduced a notion of distance in the network in the form of transmission delays between its units. These modifications necessitated the introduction of a general supervisor in order to train the network to act as a leaky integrator. When examining the lateral connection weights of the hidden layer, the distribution of the weights values was found to exhibit a conspicuous structure: the high-value weights were grouped in what we call clusters. Other zones are quite flat and characterized by low-value weights. Clusters are defined as particular groups of adjoining neurons which have strong and privileged connections with another neighborhood of neurons. The clusters of the trained network are reminiscent of the small clusters or patches that have been found experimentally in the nucleus prepositus hypoglossi, where the neural integrator is located. A study was conducted to determine the conditions of emergence of these clusters in our network: they include the fixation of the weight sign, the introduction of a distance, and a convergence of the information from the hidden layer to the motoneurons. We conclude that this spontaneous emergence of clusters in artificial neural networks; performing a temporal integration, is due to computational constraints, with a restricted space of solutions. Thus, information processing could induce the emergence of iterated patterns in biological neural networks.

Animals↗
PubMed1998

Action potential classifiers: a functional comparison of template matching, principal components analysis and an artificial neural network.

Multiunit neural activity occurs often in electrophysiological studies when utilizing extracellular electrodes. In order to estimate the activity of the individual neurons each action potential in the recording must be classified to its neuron of origin. This paper compares the accuracy of two traditional methods of action potential classification--template matching and principal components--against the performance of an artificial neural network (ANN). Both traditional methods use averages of action potential shapes to form their corresponding classifiers while the artificial neural network 'learns' a nonlinear relationship between a set of prototype action potentials and assigned classes. The set of prototypic action potentials and the assigned classes is termed the training set. The training set contained action potentials from each class which exhibited the full range of amplitude variability. The ANN provided better classification results and was more robust in analysis of across-animal data sets than either of the traditional action potential classification methods.

Action Potentials↗
PubMedDate not supplied

Broadcast scheduling in wireless multihop networks using a neural-network-based hybrid algorithm.

In wireless multihop networks, the objective of the broadcast scheduling problem is to find a conflict free transmission schedule for each node at different time slots in a fixed length time cycle, called TDMA cycle. The optimization criterion is to find an optimal TDMA schedule with minimal TDMA cycle length and maximal node transmissions. In this paper we propose a two-stage hybrid method to solve this broadcast scheduling problem in wireless multihop networks. In the first stage, we use a sequential vertex-coloring algorithm to obtain a minimal TDMA frame length. In the second stage, we apply the noisy chaotic neural network to find the maximum node transmission based on the results obtained in the previous stage. Simulation results show that this hybrid method outperforms previous approaches, such as mean field annealing, a hybrid of the Hopfield neural network and genetic algorithms, the sequential vertex coloring algorithm, and the gradual neural network.

Algorithms↗
PubMed2002

Estimating the scene illumination chromaticity by using a neural network.

A neural network can learn color constancy, defined here as the ability to estimate the chromaticity of a scene's overall illumination. We describe a multilayer neural network that is able to recover the illumination chromaticity given only an image of the scene. The network is previously trained by being presented with a set of images of scenes and the chromaticities of the corresponding scene illuminants. Experiments with real images show that the network performs better than previous color constancy methods. In particular, the performance is better for images with a relatively small number of distinct colors. The method has application to machine vision problems such as object recognition, where illumination-independent color descriptors are required, and in digital photography, where uncontrolled scene illumination can create an unwanted color cast in a photograph.

Journal Article↗
PubMed1998

Hybrid interior point training of modular neural networks.

Modular neural networks use a single gating neuron to select the outputs of a collection of agent neurons. Expectation-maximization (EM) algorithms provide one way of training modular neural networks to approximate non-linear functionals. This paper introduces a hybrid interior-point (HIP) algorithm for training modular networks. The HIP algorithm combines an interior-point linear programming (LP) algorithm with a Newton-Raphson iteration in such a way that the computational efficiency of the interior point LP methods is preserved. The algorithm is formally proven to converge asymptotically to locally optimal networks with a total computational cost that scales in a polynomial manner with problem size. Simulation experiments show that the HIP algorithm produces networks whose average approximation error is better than that of EM-trained networks. These results also demonstrate that the computational cost of the HIP algorithm scales at a slower rate than the EM-procedure and that, for small-size networks, the total computational costs of both methods are comparable.

Journal Article↗
PubMed2005

Ab initio potential-energy surfaces for complex, multichannel systems using modified novelty sampling and feedforward neural networks.

A neural network/trajectory approach is presented for the development of accurate potential-energy hypersurfaces that can be utilized to conduct ab initio molecular dynamics (AIMD) and Monte Carlo studies of gas-phase chemical reactions, nanometric cutting, and nanotribology, and of a variety of mechanical properties of importance in potential microelectromechanical systems applications. The method is sufficiently robust that it can be applied to a wide range of polyatomic systems. The overall method integrates ab initio electronic structure calculations with importance sampling techniques that permit the critical regions of configuration space to be determined. The computed ab initio energies and gradients are then accurately interpolated using neural networks (NN) rather than arbitrary parametrized analytical functional forms, moving interpolation or least-squares methods. The sampling method involves a tight integration of molecular dynamics calculations with neural networks that employ early stopping and regularization procedures to improve network performance and test for convergence. The procedure can be initiated using an empirical potential surface or direct dynamics. The accuracy and interpolation power of the method has been tested for two cases, the global potential surface for vinyl bromide undergoing unimolecular decomposition via four different reaction channels and nanometric cutting of silicon. The results show that the sampling methods permit the important regions of configuration space to be easily and rapidly identified, that convergence of the NN fit to the ab initio electronic structure database can be easily monitored, and that the interpolation accuracy of the NN fits is excellent, even for systems involving five atoms or more. The method permits a substantial computational speed and accuracy advantage over existing methods, is robust, and relatively easy to implement.

Journal Article↗
PubMed1996

Memory and Learning of Sequential Patterns by Nonmonotone Neural Networks.

Conventional neural network models for temporal association generally do not work well in the absence of synchronizing neurons. This is because their dynamical properties are fundamentally not suitable for storing sequential patterns, no matter what storage or learning algorithm is used. The present article describes a nonmonotone neural network (NNN) model in which sequential patterns are stored by being embedded in a trajectory attractor of the dynamical system, and recalled stably and smoothly without synchronization; recall is done in such a way that the network state successively moves along the trajectory. A simple and natural learning algorithm for the NNN is also presented, where one only has to vary the input pattern gradually and modify the synaptic weights according to a kind of covariance rule; then the network state follows slightly behind the input pattern, and its trajectory grows to be an attractor with a small number of repetitions. Copyright 1996 Elsevier Science Ltd.

Journal Article↗
PubMed1998

[Testing the identity of hashish samples with ICP-AES and NAA and data handling with neural networks. 2. Data verification with the use of artificial neural networks].

Twenty different hashish samples, which were confiscated in Irak, Iran, Bulgaria, Switzerland, Great Britain and Germany were analysed by means of NAA and ICP-AES. We used modified ANNs to identify a repeated analysed sample out of that data pool. The ANNs are described. Especially the learning rule, a modified backpropagation method, is presented. It is obvious, that neural networks can solve the described classification tasks. There is no significant difference in the power of the applied analytical methods.

Cannabis↗
PubMed2000

Simulation of cognitive disturbances by a dynamic threshold semantic neural network.

A neural network model with dynamic thresholds, asymmetric connections, and clustered memories simulates spread activation that is hypothesized for semantic networks in the brain. By altering the parameters of the dynamic threshold a large range of disturbances can be generated in the model. These disturbances show metaphorical resemblance to certain general clinical descriptions of mental disturbances found in psychiatric patients engaged in various cognitive tasks. Even though the model is highly theoretical and metaphoric, it may help to gain certain insights into the relation between alterations of certain neural parameters, for example, thresholds and connectivity, and clinical symptoms in patients.

Algorithms↗
PubMed2004

Encoding nondeterministic fuzzy tree automata into recursive neural networks.

Fuzzy neural systems have been a subject of great interest in the last few years, due to their abilities to facilitate the exchange of information between symbolic and subsymbolic domains. However, the models in the literature are not able to deal with structured organization of information, that is typically required by symbolic processing. In many application domains, the patterns are not only structured, but a fuzziness degree is attached to each subsymbolic pattern primitive. The purpose of this paper is to show how recursive neural networks, properly conceived for dealing with structured information, can represent nondeterministic fuzzy frontier-to-root tree automata. Whereas available prior knowledge expressed in terms of fuzzy state transition rules are injected into a recursive network, unknown rules are supposed to be filled in by data-driven learning. We also prove the stability of the encoding algorithm, extending previous results on the injection of fuzzy finite-state dynamics in high-order recurrent networks.

Algorithms↗
PubMed1998

Using neural networks as an aid in the determination of disease status: comparison of clinical diagnosis to neural-network predictions in a pedigree with autosomal dominant limb-girdle muscular dystrophy.

Studies of the genetics of certain inherited diseases require expertise in the determination of disease status even for single-locus traits. For example, in the diagnosis of autosomal dominant limb-girdle muscular dystrophy (LGMD1A), it is not always possible to make a clear-cut determination of disease, because of variability in the diagnostic criteria, age at onset, and differential presentation of disease. Mapping such diseases is greatly simplified if the data present a homogeneous genetic trait and if disease status can be reliably determined. Here, we present an approach to determination of disease status, using methods of artificial neural-network analysis. The method entails "training" an artificial neural network, with input facts (based on diagnostic criteria) and related results (based on disease diagnosis). The network contains weight factors connecting input "neurons" to output "neurons," and these connections are adjusted until the network can reliably produce the appropriate outputs for the given input facts. The trained network can be "tested" with a second set of facts, in which the outcomes are known but not provided to the network, to see how well the training has worked. The method was applied to members of a pedigree with LGMD1A, now mapped to chromosome 5q. We used diagnostic criteria and disease status to train a neural network to classify individuals as "affected" or "not affected." The trained network reproduced the disease diagnosis of all individuals of known phenotype, with 98% reliability. This approach defined an appropriate choice of clinical factors for determination of disease status. Additionally, it provided insight into disease classification of those considered to have an "unknown" phenotype on the basis of standard clinical diagnostic methods.

Adolescent↗
PubMed1991

Computer recognition of brain stem auditory evoked potential wave V by a neural network.

A neural network simulator was used to create a connectionist model for the recognition of the peak of wave V of the brain stem auditory evoked potential (BAEP) test. Wave forms were selected from BAEPs performed in the last four years at the University of Pittsburgh Presbyterian University Hospital (PUH). The ipsilateral and contralateral wave forms were digitized and then sampled at 0.1 msec intervals using linear interpolation. The resulting amplitudes were normalized to the range less than -1, 1 greater than. The normalized amplitudes were used as the initial activation values for the processing elements of the input layer. The desired outputs (the target locations for wave V) were determined by adjusting the latencies recorded by the physician interpreter for any distortion in the digitizing process. The location of wave V was represented in the output layer by setting the output element which correspond to the target location and its immediate neighbors to high activation levels and all the remaining output units to zero activity. Two network architectures, differing only in the hidden unit layer, with 40 and 16 hidden units respectively, were used. The networks were trained using standard back-propagation. Several trials from different starting points were performed for each architecture. The training set was composed of the wave forms resulting from the stimulation of 50 ears. The best network, found after 60 epochs (3000 presentations) was able to correctly identify 17 out of 20 cases (85%) from a set of test cases which were independent from the training set.

Diagnosis, Computer-Assisted↗
PubMed1992

Computer recognition of brain stem auditory evoked potential wave V by a neural network.

A neural network simulator was used for the recognition of the presence and location of the peak of wave V of the brain stem auditory evoked potential (BAEP) test. Waveforms selected from BAEPs performed in the last 4 years at the University of Pittsburgh Presbyterian University Hospital were digitized and sampled, and the resulting amplitudes were normalized. A training set was composed of the waveforms resulting from the stimulation of 50 ears. The normalized amplitudes were used as the initial activation values for the networks. The desired outputs (the target locations for wave V) were represented in the output layer by setting the output element, which corresponded to the target location and its immediate neighbors, to high activation levels, and all the remaining output units to zero activity. Two network architectures, differing only in the hidden unit layer, with 40 and 16 hidden units, respectively, were trained by using standard back-propagation. Several trials from different starting points were performed for each architecture. The best network, found after 60 epochs (3,000 presentations), was able to correctly identify 17 of 20 cases (85%) from a set of test cases that were independent from the training set.

Evaluation Studies as Topic↗
PubMed2001

Adaptive control of mobile robots using a neural network.

A Neural Network - based control approach for mobile robot is proposed. The weight adaptation is made on-line, without previous learning. Several possible situations in robot navigation are considered, including uncertainties in the model and presence of disturbance. Weight adaptation laws are presented as well as simulation results.

Neural Networks, Computer↗
PubMed2004

Gaussian filters and filter synthesis using a Hermite/Laguerre neural network.

A neural network for calculating the correlation of a signal with a Gaussian function is described. The network behaves as a Gaussian filter and has two outputs: the first approximates the noisy signal and the second represents the filtered signal. The filtered output provides improvement by a factor of ten in the signal-to-noise ratio. A higher order Gaussian filter was synthesized by combining several Hermite functions together.

Neural Networks, Computer↗
PubMed1990

Efficient recognition of immunoglobulin domains from amino acid sequences using a neural network.

A neural network was trained using back propagation to recognize immunoglobulin domains from amino acid sequences. The program was designed to identify proteins exhibiting such domains with minimal rates of false positives and false negatives. The National Biomedical Research Foundation NEW protein sequences database was scanned to evaluate the performance of the program in recognizing mouse immunoglobulin sequences. The program correctly recognized 55 out of 56 mouse immunoglobulin sequences, corresponding to a recognition efficiency of 98.2% with an overall false positive rate of 7.3%. These data demonstrate that neural network-based search programs are well suited to search for sequences characterized by only a few well-conserved subsequences.

Algorithms↗