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.

SourceResearch connectionFrom yearThrough year

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

At least 1,459 records · Page 81Linked to original sources

PubMed1996

Gaussian ARTMAP: A Neural Network for Fast Incremental Learning of Noisy Multidimensional Maps.

A new neural network architecture for incremental supervised learning of analog multidimensional maps is introduced. The architecture, called Gaussian ARTMAP, is a synthesis of a Gaussian classifier and an adaptive resonance theory (ART) neural network, achieved by defining the ART choice function as the discriminant function of a Gaussian classifier with separable distributions, and the ART match function as the same, but with the distributions normalized to a unit height. While Gaussian ARTMAP retains the attractive parallel computing and fast learning properties of fuzzy ARTMAP, it learns a more efficient internal representation of a mapping while being more resistant to noise than fuzzy ARTMAP on a number of benchmark databases. SSeveral simulations are presented which demonstrate that Gaussian ARTMAP consistently obtains a better trade-off of classification rate to number of categories than fuzzy ARTMAP. Results on a vowel classification problem are also presented which demonstrate that Gaussian ARTMAP outperforms many other classifiers. Copyright 1996 Elsevier Science Ltd

Journal Article↗

PubMed2005

The self-trapping attractor neural network--part II: properties of a sparsely connected model storing multiple memories.

In a previous paper, the self-trapping network (STN) was introduced as more biologically realistic than attractor neural networks (ANNs) based on the Ising model. This paper extends the previous analysis of a one-dimensional (1-D) STN storing a single memory to a model that stores multiple memories and that possesses generalized sparse connnectivity. The energy, Lyapunov function, and partition function derived for the 1-D model are generalized to the case of an attractor network with only near-neighbor synapses, coupled to a system that computes memory overlaps. Simulations reveal that 1) the STN dramatically reduces intra-ANN connectivity without severly affecting the size of basins of attraction, with fast self-trapping able to sustain attractors even in the absence of intra-ANN synapses; 2) the basins of attraction can be controlled by a single free parameter, providing natural attention-like effects; 3) the same parameter determines the memory capacity of the network, and the latter is much less dependent than a standard ANN on the noise level of the system; 4) the STN serves as a useful memory for some correlated memory patterns for which the standard ANN totally fails; 5) the STN can store a large number of sparse patterns; and 6) a Monte Carlo procedure, a competitive neural network, and binary neurons with thresholds can be used to induce self-trapping.

Algorithms↗

PubMedDate not supplied

Recognition of the bouquet of Chinese spirits by artificial neural network analysis.

Forty-six samples of Chinese spirits, whose bouquets were determined by sensory evaluations, and 17 compounds characteristic of the flavors determined by gas chromatography/gas chromatography-mass spectrometry (GC/GC-MS), were subjected to neural network analysis and their corresponding factor scores developed. To make the bouquet recognition more efficient, an improved artificial back-propagation neural network (BPNN) was applied. In each kind of data, the BPNN was trained repeatedly until the error rate was less than the predetermined threshold error; then the trained network was applied to the test set that was not involved in the training process to establish the validity of the network, and a correct prediction rate of 100% was obtained. The BPNN provided a correlation between the data offered from sensory evaluations and the data of chemical compositions determined by instrumental analysis. The BPNN approach is feasible regardless of whether the crude data or the factor scores are used; however, recognition results were better with the latter than with the former. In a comparison of all the results obtained by BPNN, cluster analysis, and discriminant analysis, the method of artificial neural network analysis appeared to be the optimal technique for recognizing the bouquet of Chinese spirits.

Alcoholic Beverages↗

PubMed1991

Identification of the 1H-NMR spectra of complex oligosaccharides with artificial neural networks.

Artificial networks can be used to identify hydrogen nuclear magnetic resonance (1H-NMR) spectra of complex oligosaccharides. Feed-forward neural networks with back-propagation of errors can distinguish between spectra of oligosaccharides that differ by only one glycosyl residue in twenty. The artificial neural networks use features of the strongly overlapping region of the spectra (hump region) as well as features of the resolved regions of the spectra (structural reporter groups) to recognize spectra and efficiently recognized 1H-NMR spectra even when the spectra were perturbed by minor variations in their chemical shifts. Identification of spectra by neural network-based pattern recognition techniques required less than 0.1 second. It is anticipated that artificial neural networks can be used to identify the structures of any complex carbohydrate that has been previously characterized and for which a 1H-NMR spectrum is available.

Artificial Intelligence↗

PubMed1994

Electrode potentials for bioreductive agents from neural networks.

The one-electron electrode potentials at pH 7 have been predicted to an average accuracy of about 70 mV for a number of nitrobenzenes, nitrofurans and nitroimidazoles using a neural network. The inputs were the heat of formation and the free energy of hydration of both the nitroarene and its radical anion. The heats of formation were calculated using semiempirical molecular orbital methods; the free energies of hydration were calculated using a modified Born equation with additional semiempirical terms. Since these inputs can be calculated quickly, the neural network promises to be very useful in the design of molecules such as bioreductive agents where the electrode potential is of crucial importance. The success of the neural network in this problem implies that the errors, primarily in the semiempirical heat of formation, are systematic, and offers the hope that these may be corrected in future generations of the semiempirical methods.

Antineoplastic Agents↗

PubMed1996

Use of neural networks to diagnose acute myocardial infarction. I. Methodology.

We investigated several aspects of using neural networks as a diagnostic tool: the design of an optimal network, the amount of patients' data needed to train the network, the question of training the network optimally while avoiding overfitting, and the influence of redundant variables. The specific clinical problem chosen for illustration was the diagnosis of acute myocardial infarction, given only the electrocardiogram and the concentration of potassium in serum at the time of admission. We found that, in contrast to usual practice, the termination of the training process should be based on the generalization performance and not on the training performance. We also found that a principal component analysis can be used to eliminate redundant variables, thereby reducing the data space. The diagnostic performance of the neural network we used was 78%--superior to that of linear discriminant function analysis but similar to that of quadratic discriminant function analysis.

Diagnosis, Computer-Assisted↗

PubMed1994

NNERVE: neural network extraction of repetitive vectors for electromyography--Part II: Performance analysis.

We have presented a new method for the decomposition of clinical electromyographic signals, NNERVE, which utilizes a novel "pseudo-unsupervised" neural network approach to signal decomposition. In this paper, we present a detailed performance analysis. We present definitions for quantitative performance criteria. NNERVE is shown to be highly reliable over a wide range of neural network architectures. It is also minimally sensitive to learning parameters. The degradations of performance over a wide range of signals and parameters are shown to be gradual, slight and graceful. These characteristics are shown to translate directly into a high degree of robustness over widely varying signals. Real signals obtained from the entire range of patients encountered in clinical situations are shown to be correctly handled without any modifications or adjustments of any parameters. This neural network method is then directly compared to a prior traditional signal processing method and is shown quantitatively to have consistently superior performance on both simulated and real signals. Clinically acceptable performance over a wide range of signals, recorded using standard clinical methodology, and the lack of a need for user interaction, will facilitate the use of motor unit quantitation in routine clinical electromyography.

Algorithms↗

PubMed2002

Ultrasound estimation of fetal weight with the use of computerized artificial neural network model.

The aim of this study was to test if the computerized artificial neural network (ANN) model could improve ultrasound (US) estimation of fetal weight over estimation with the other commonly used formulas generated from regression analysis. First, as the training group, we performed US examinations on 991 singleton fetuses within 3 days of delivery. Six input variables were used to construct the ANN model: biparietal diameter (BPD), occipitofrontal diameter (OFD), abdominal circumference (AC), femur length (FL), gestational age and fetal presentation. Second, a total of 362 fetuses were assessed subsequently as the validation group. In this training group, the ANN model was better than the other compared formulas in fetal weight estimation (n = 991, mean absolute error 183.83 g, mean absolute percent error 6.02%, all p < 0.0001). In addition, the validation group further proved the results (n = 362, mean absolute error 179.91 g, mean absolute percent error 6.15%, all p < 0.005). In conclusion, the computerized artificial neural network (ANN) model could provide better US estimation of fetal weight than estimations by means of commonly used formulas generated from regression analysis.

Female↗

PubMed2004

Obstacle avoidance for kinematically redundant manipulators using a dual neural network.

One important issue in the motion planning and control of kinematically redundant manipulators is the obstacle avoidance. In this paper, a recurrent neural network is developed and applied for kinematic control of redundant manipulators with obstacle avoidance capability. An improved problem formulation is proposed in the sense that the collision-avoidance requirement is represented by dynamically-updated inequality constraints. In addition, physical constraints such as joint physical limits are also incorporated directly into the formulation. Based on the improved problem formulation, a dual neural network is developed for the online solution to collision-free inverse kinematics problem. The neural network is simulated for motion control of the PA10 robot arm in the presence of point and window-shaped obstacle.

Journal Article↗

PubMed1994

Mapping myocardial activation distributions using neural networks: 2-D simulation results.

The goal of this study was to explore the capabilities of neural networks to map with accuracy the sequence and location of myocardial activation using QRS complexes simulating normal and altered activation. A two-dimensional (2-D) fractal-based computer model of myocardial activation was used to develop training data for initial network learning. Two types of activation scenarios were used to evaluate network learning: 1) 450 training sets based on three activation foci per set using randomly chosen times and activation sites, and 2) 199 training sets based on a sequential, hierarchical blocking of the fractal-based model conduction network. Network learning was evaluated with training and test cases using trained weights. Network-calculated activation maps compared with the target activation maps had a mean error of < 5% in assigning the site and timing of activation. Pointwise mean correlation coefficients were > 0.98 for all conduction network cases and > 0.84 for the more demanding point foci cases. We conclude, based on these simulation results, that neural networks may be used to calculate activation maps using electrocardiogram lead data for a variety of activation patterns.

Animals↗

PubMed2000

Neural networks in analog hardware--design and implementation issues.

This paper presents a brief review of some analog hardware implementations of neural networks. Several criteria for the classification of general neural networks implementations are discussed and a taxonomy induced by these criteria is presented. The paper also discusses some characteristics of analog implementations as well as some trade-offs and issues identified in the work reviewed. Parameters such as precision, chip area, power consumption, speed and noise susceptibility are discussed in the context of neural implementations. A unified review of various "VLSI friendly" algorithms is also presented. The paper concludes with some conclusions drawn from the analysis of the implementations presented.

Artificial Intelligence↗

PubMed2006

Evaluation of neural network robust reliability using information-gap theory.

A novel technique for the evaluation of neural network robustness against uncertainty using a nonprobabilistic approach is presented. Conventional optimization techniques were employed to train multilayer perceptron (MLP) networks, which were then probed with an uncertainty analysis using an information-gap model to quantify the network response to uncertainty in the input data. It is demonstrated that the best performing network on data with low uncertainty is not in general the optimal network on data with a higher degree of input uncertainty. Using the concepts of information-gap theory, this paper develops a theoretical framework for information-gap uncertainty applied to neural networks, and explores the practical application of the procedure to three sample cases. The first consists of a simple two-dimensional (2-D) classification network operating on a known Gaussian distribution, the second a nine-lass vibration classification problem from an aircraft wing, and the third a two-class example from a database of breast cancer incidence.

Algorithms↗

PubMed1989

Neural network models for promoter recognition.

The problem of recognition of promoter sites in the DNA sequence has been treated with models of learning neural networks. The maximum network capacity admissible for this problem has been estimated on the basis of the total of experimental data available on the determined promoter sequences. The model of a block neural network has been constructed to satisfy this estimate and rules have been elaborated for its learning and testing. The learning process involves a small (of the order of 10%) part of the total set of promoter sequences. During this procedure the neural network develops a system of distinctive features (key words) to be used as a reference in identifying promoters against the background of random sequences. The learning quality is then tested with the whole set. The efficiency of promoter recognition has been found to amount to 94 to 99%. The probability of an arbitrary sequence being identified as a promoter is 2 to 6%.

Base Sequence↗

PubMed2005

Artificial neural network modeling of apoptosis in gamma irradiated human lymphocytes.

PURPOSE: To develop an artificial neural network (ANN) model of apoptotic response in gamma irradiated human lymphocytes. To assess the feasibility of training ANN radiobiological models using data collected with flow cytometry. MATERIALS AND METHODS: Irradiated isolated human lymphocytes were labelled with Annexin V-Fluorescein Isothiocyanate (FITC) and 7-Amino-Actinomycin D (7AAD) then analysed using flow cytometry. Twenty-four dose responses per donor from 14 donors were collected from a flow cytometer and used in model development as the training and cross-validation datasets. The general ANN model architecture was a multi-layer perceptron using the mean squared error of a cross validation dataset as the objective function. The ANN model was optimized by varying the number of hidden layers and the number of processing elements per layer. The optimized model constituted of three hidden layers with 80, 40, and 10 hidden layers in the first, second, and third layers respectively. RESULTS: The optimized model was used to simulate dose responses at the training doses of 0, 2, 4 and 8 Gray. A strong agreement between the model and measured dose responses was observed. The model was also used to simulate a dose response at 0.1 Gray and results were compared to the measured dose response from a donor not used in model development. Again, strong agreement between the model and the observed dose response was found. CONCLUSIONS: This study shows that artificial neural networks can be trained to provide high resolution, high accuracy models of multivariate radiobiological data collected by flow cytometry.

Apoptosis↗

PubMed2007

The road to chaos by time-asymmetric Hebbian learning in recurrent neural networks.

This letter aims at studying the impact of iterative Hebbian learning algorithms on the recurrent neural network's underlying dynamics. First, an iterative supervised learning algorithm is discussed. An essential improvement of this algorithm consists of indexing the attractor information items by means of external stimuli rather than by using only initial conditions, as Hopfield originally proposed. Modifying the stimuli mainly results in a change of the entire internal dynamics, leading to an enlargement of the set of attractors and potential memory bags. The impact of the learning on the network's dynamics is the following: the more information to be stored as limit cycle attractors of the neural network, the more chaos prevails as the background dynamical regime of the network. In fact, the background chaos spreads widely and adopts a very unstructured shape similar to white noise. Next, we introduce a new form of supervised learning that is more plausible from a biological point of view: the network has to learn to react to an external stimulus by cycling through a sequence that is no longer specified a priori. Based on its spontaneous dynamics, the network decides "on its own" the dynamical patterns to be associated with the stimuli. Compared with classical supervised learning, huge enhancements in storing capacity and computational cost have been observed. Moreover, this new form of supervised learning, by being more "respectful" of the network intrinsic dynamics, maintains much more structure in the obtained chaos. It is still possible to observe the traces of the learned attractors in the chaotic regime. This complex but still very informative regime is referred to as "frustrated chaos."

Algorithms↗

PubMed2004

A neural network based prediction of octanol-water partition coefficients using atomic5 fragmental descriptors.

An artificial neural network based approach using Atomic5 fragmental descriptors has been developed to predict the octanol-water partition coefficient (logP). We used a pre-selected set of organic molecules from PHYSPROP database as training and test sets for a feedforward neural network. Results demonstrate the superiority of our non-linear model over the traditional linear method.

Models, Chemical↗

PubMed2001

Use of neural network models to predict industrial bioreactor effluent quality.

Engineered bioreactors are useful tools for degrading wastes from crude oil refining facilities. One such bioreactor forms part of the wastewater remediation process used at a refinery in the San Francisco Bay Area. The flow rate and chemical concentrations of the waste vary, and it is necessary to be able to predict the efficiency of the reactor degradation process for this varied input. The complex biological, physical, and chemical processes of the reactor make deterministic modeling unsuitable. Therefore, predictive modeling for this system was performed using a neural network model. A predictive, time-series neural network model requires a complete data set. Often, in the case of a large industrial facility, data are missing. Various techniques can be used to reconstruct missing data, but comparisons of techniques have not been performed for large-scale remediation processes. In this manuscript, four techniques are used for reconstructing missing data to examine which ones provide superior predictive capabilities. It was found that the interpolated and moving average values methods provided the best predictions. The mean and median replacement methods, commonly used in neural network modeling, provided much poorer predictions. Another goal of this study is to determine which water quality parameters are more accurately predicted than others. In this study, pH was the most accurately predicted, while ammonia and total phenolics concentrations were the least accurately predicted.

Ammonia↗

PubMed2006

Applications of neural network methods to the processing of earth observation satellite data.

The new generation of earth observation satellites carries advanced sensors that will gather very precise data for studying the Earth system and global climate. This paper shows that neural network methods can be successfully used for solving forward and inverse remote sensing problems, providing both accurate and fast solutions. Two examples of multi-neural network systems for the determination of cloud properties and for the retrieval of total columns of ozone using satellite data are presented. The developed algorithms based on multi-neural network are currently being used for the operational processing of European atmospheric satellite sensors and will play a key role in related satellite missions planed for the near future.

Computer Simulation↗