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 595 records · Page 33Linked to original sources
PubMed2000

Classification of clinical autofluorescence spectra of oral leukoplakia using an artificial neural network: a pilot study.

The performance of an artificial neural network was evaluated as an alternative classification technique of autofluorescence spectra of oral leukoplakia, which may reflect the grade of tissue dysplasia. Twenty-two visible lesions of 21 patients suffering from oral leukoplakia and six locations on normal oral mucosa of volunteers were investigated with autofluorescence spectroscopy (420 nm excitation, 465-650 nm emission). Pre-scaled spectra were combined with the corresponding visual and histopathological classifications in order to train artificial neural networks. A trained network is mapping input spectra to tissue characteristics, which was evaluated using a blind set of spectra. Abnormal tissue could be distinguished from normal tissue by a neural network with a sensitivity of 86% and a specificity of 100%. Also, classifying either homogeneous or non-homogeneous tissue performed reasonably well. Weak or no correlation existed between spectral patterns and verrucous or erosive tissue or the grade of dysplasia, hyperplasia and hyperkeratosis.

Adult↗
PubMed2004

Digit and command interpretation for electronic book using neural network and genetic algorithm.

This paper presents the interpretation of digits and commands using a modified neural network and the genetic algorithm. The modified neural network exhibits a node-to-node relationship which enhances its learning and generalization abilities. A digit-and-command interpreter constructed by the modified neural networks is proposed to recognize handwritten digits and commands. A genetic algorithm is employed to train the parameters of the modified neural networks of the digit-and-command interpreter. The proposed digit-and-command interpreter is successfully realized in an electronic book. Simulation and experimental results will be presented to show the applicability and merits of the proposed approach.

Algorithms↗
PubMed1992

A practical application of neural network analysis for predicting outcome of individual breast cancer patients.

It has been previously shown that Neural Networks can be trained to recognize individual breast cancer patients at high and low risk for recurrent disease and death. This paper expands on the initial investigation and shows that by coding time as one of the prognostic variables, a Neural Network can use censored survival data to predict patient outcome over time. In this demonstration a Neural Network was trained, tested, and validated using censored survival data from a group of 1373 patients with node-positive breast cancer. The Neural Network method predicted patient outcome as accurately as Cox Regression modeling. The final Neural Network model can be presented with a patient's prognostic information and make a series of predictions about probability of relapse at different times of follow-up, allowing one to draw survival probability curves for individual patients.

Adult↗
PubMed1993

Identification of peak V in brainstem auditory evoked potentials with neural networks.

A feature extractor for determining the latency of peak V in brainstem auditory evoked potentials (BAEPs) is presented in this paper. A feature extractor that combines artificial neural networks with an algorithmic approach is presented. It consists of a series of small neural networks that have to make simple decisions. Each neural network decides what part of the input pattern contains the peak, and the algorithm passes that part of the pattern to the next neural network; in this way the size of the input patterns decreases during the process, and the last neural network determines the exact location of the peak. An optimal configuration of neural networks could determine the latencies of peak V in all synthetic evoked potentials correctly. With real evoked potentials, the networks yield results that comply with the opinion of a human expert in 80 +/- 6% of the cases.

Adult↗
PubMed2002

Application of artificial neural networks to combinatorial catalysis: modeling and predicting ODHE catalysts.

This paper shows how artificial neural networks are useful for modeling catalytic data from combinatorial catalysis and for predicting new potential catalyst compositions for the oxidative dehydrogenation of ethane (ODHE). The training and testing sets of data used for the neural network studies were obtained by means of a combinatorial approach search, which employs an evolutionary optimization strategy. Input and output variables of the neural network include the molar composition of thirteen different elements presented in the catalyst and five catalytic performances (C2H6 and O2 conversion, C2H4 yield, and C2H4, CO2, and CO selectivity). The fitting results indicate that neural networks can be useful in high-dimensional data management within combinatorial catalysis search procedures, since neural networks allow the ab initio evaluation of the reactivity of multicomponent catalysts.

Journal Article↗
PubMed1993

Clinical decisions for psychiatric inpatients and their evaluation by a trained neural network.

Ninety-two consecutive treatment decisions regarding psychotic and depressed inpatients were evaluated by a trained neural network. Simultaneous evaluations according to the Brief Psychiatric Rating Scale (BPRS), the Hamilton scale, and the neural network were performed. A 15-point decrease in the BPRS for psychotic patients or a 10-point decrease in the Hamilton scale for depressed patients was the cut-off point for treatment success. The neural network performed similarly to the clinicians. The combined clinician-network success rate reached 79% and was significantly higher than that for each alone. Clinicians and neural network disagreed on 62% of decisions made for depressed patients and on 55% of decisions made for psychotic patients. The proportion of agreement was lower in both diagnostic groups than expected by chance. However, the high success of the combined clinician and neural network decisions and the high rate of mutual disagreement may imply that a combined decision is fruitful.

Depressive Disorder↗
PubMed1997

Current keratoconus detection methods compared with a neural network approach.

PURPOSE: Four videokeratographic methods for keratoconus detection were compared with a neural network approach. METHODS: A classification neural network for keratoconus screening was designed to detect the presence of keratoconus (KC) or keratoconus suspects (KCS); a separate cone severity network graded the severity of conelike topography patterns consistent with KC or KCS. Three hundred TMS-1 examinations (Tomey) were randomly divided into training and test sets. Ten topographic indexes were network inputs. Nine categories were used: normal, astigmatism, KC, KCS, contact lens-induced warpage, pellucid marginal degeneration, photorefractive keratectomy, radial keratotomy, and penetrating keratoplasty. KC was subdivided into KC1 (mild), KC2 (moderate), and KC3 (advanced). There were three outputs for the classification network (KC, KCS, and OTHER); target output values of 0 = OTHER, 0.25 = KCS, 0.5 = KC1, 0.75 = KC2, and 1.0 = KC3 were used for the severity network. RESULTS: The best-trained classification network had 100% accuracy, specificity, and sensitivity for the test set. The severity network had mean outputs (+/-standard deviation) of OTHER = 0.02+/-0.02, KCS = 0.21+/-0.05, KC1 = 0.52+/-0.17, KC2 = 0.74+/-0.12, and KC3 = 0.91+/-0.15. The severity network output for all categories was well correlated to the keratoconus prediction index (R = 0.892, P < 0.0001). The classification network had an overall accuracy and specificity significantly better (P < or = 0.005) than the Klyce/Maeda keratoconus index (KCI) test, the Rabinowitz test (K & I-S), and simulated keratometry (average Sim K). However, there were no significant differences in keratoconus sensitivity between the classification network, KCI, and K & I-S. The sensitivity and specificity of average Sim K were significantly worse than those of the other tests. The classification network had significantly better sensitivity (P < 0.001) and specificity (P = 0.025) for KCS detection than the K & I-S. CONCLUSIONS: The neural networks completely distinguished KC from KCS and from topographies that resembled KC. The network approach equaled the sensitivity of currently used tests for keratoconus detection and outperformed them in terms of accuracy and specificity.

Cornea↗
PubMed2006

Eigenvalue spectra of random matrices for neural networks.

The dynamics of neural networks is influenced strongly by the spectrum of eigenvalues of the matrix describing their synaptic connectivity. In large networks, elements of the synaptic connectivity matrix can be chosen randomly from appropriate distributions, making results from random matrix theory highly relevant. Unfortunately, classic results on the eigenvalue spectra of random matrices do not apply to synaptic connectivity matrices because of the constraint that individual neurons are either excitatory or inhibitory. Therefore, we compute eigenvalue spectra of large random matrices with excitatory and inhibitory columns drawn from distributions with different means and equal or different variances.

Models, Theoretical↗
PubMed1996

Using artificial bat sonar neural networks for complex pattern recognition: recognizing faces and the speed of a moving target.

Two sets of studies examined the viability of using bat-like sonar input for artificial neural networks in complex pattern recognition tasks. In the first set of studies, a sonar neural network was required to perform two face recognition tasks. In the first task, the network was trained to recognize different faces regardless of facial expressions. Following training, the network was tested on its ability to generalize and correctly recognize faces using echoes of novel facial expressions that were not included in the training set. The neural network was able to recognize novel echoes of faces almost perfectly (above 96% accuracy) when it was required to recognize up to five faces. In the second face recognition task, a sonar neural network was trained to recognize the sex of 16 faces (eight males and eight females). After training, the network was able to correctly recognize novel echoes of those faces as 'male' or as 'female' faces with accuracy levels of 88%. However, the network was not able to recognize novel faces as 'male' or 'female' faces. In the second set of studies, a sonar neural network was required to learn to recognize the speed of a target that was moving towards the viewer. During training, the target was presented in a variety of orientations, and the network's performance was evaluated when the target was presented in novel orientations that were not included in the training set. The different orientations dramatically affected the amplitude and the frequency composition of the echoes. The neural network was able to learn and recognize the speed of a moving target, and to generalize to new orientations of the target. However, the network was not able to generalize to new speeds that were not included in the training set. The potential and limitations of using bat-like sonar as input for artifical neural networks are discussed.

Adult↗
PubMed2002

An evolutionary artificial neural networks approach for breast cancer diagnosis.

This paper presents an evolutionary artificial neural network (EANN) approach based on the pareto-differential evolution (PDE) algorithm augmented with local search for the prediction of breast cancer. The approach is named memetic pareto artificial neural network (MPANN). Artificial neural networks (ANNs) could be used to improve the work of medical practitioners in the diagnosis of breast cancer. Their abilities to approximate nonlinear functions and capture complex relationships in the data are instrumental abilities which could support the medical domain. We compare our results against an evolutionary programming approach and standard backpropagation (BP), and we show experimentally that MPANN has better generalization and much lower computational cost.

Algorithms↗
PubMed2002

Quantitative structure-activity relationships by evolved neural networks for the inhibition of dihydrofolate reductase by pyrimidines.

Evolutionary computation provides a useful method for training neural networks in the face of multiple local optima. This paper begins with a description of methods for quantitative structure activity relationships (QSAR). An overview of artificial neural networks for pattern recognition problems such as QSAR is presented and extended with the description of how evolutionary computation can be used to evolve neural networks. Experiments are conducted to examine QSAR for the inhibition of dihydrofolate reductase by pyrimidines using evolved neural networks. Results indicate the utility of evolutionary algorithms and neural networks for the predictive task at hand. Furthermore, results that are comparable or perhaps better than those published previously were obtained using only a small fraction of the previously required degrees of freedom.

Biological Evolution↗
PubMed2004

Qualitative diagnosis of calvarial metastasis by neural network and logistic regression.

RATIONALE AND OBJECTIVES: To simplify the diagnostic features used by an artificial neural network compared with logistic regression (LR) in the diagnosis of calvarial metastasis with computed tomography and analyze their accuracy. MATERIALS AND METHODS: Twenty-one of 167 patients with calvarial lesions were found to have metastasis. Clinical and computed tomography data were used for LR and neural network models. Both models were tested with the leave-one-out method. The final results of each model were compared using the area under receiver operating characteristic curve (Az). RESULTS: The neural network identified metastasis significantly more successfully than LR with an Az of 0.9324 +/- 0.0386 versus 0.9192 +/- 0.0373, P = .01. The most important features selected by the LR and neural network were age and edge definition. CONCLUSION: Neural networks offer wide possibilities over statistics for the study of calvarial metastases other than their minimum clinical and radiologic features for diagnosis.

Adolescent↗
PubMed1975

Associative recall and formation of stable modes of activity in neural network models.

Models of neural networks with recurrent inhibition are studied, as well as one model which also includes recurrent excitation. The models are intended as possible descriptions of the cerebral cortex. Each network model is composed of neuron models called pyramidal cells and stellate cells in accordance with the names of two types of cells in the cortex. Inputs and outputs of the network are connected to the pyramidal cells while feedback is provided by the stellate cells. Connections within the network are random. During a learning phase the pyramidal cell excitatory synapses become facilitated according to a two-conditional facilitation rule. This is the basis of the model's ability for associative learning. The associative retrieval of information can be studied during a subsequent association phase. This has been done by simulation on a digital computer. It was shown that all of the models considered can be designed to perform a so-called decision-making function. This means that if the associating input pattern is similar to several patterns which occurred during learning the model can decide which similarity is greatest by responding with the appropriate associated pattern. The model also including recurrent excitation differs from the simpler models in that it can become stabilized in so-called stable modes of activity which are self-sustaining and remain even after the input has been turned off. Normally, only one stable mode can be active at a time. However, through careful choice of construction parameters it was possible to obtain a model in which a maximum of two stable modes could be activated independently of each other. Physiological and psychological interpretations are discussed and so are the limitations of the models, which are evident in certain situations.

Cerebral Cortex↗
PubMedDate not supplied

Neural networks in radiology: an introduction and evaluation in a signal detection task.

Neural networks are a computer architecture, implementable in software or hardware, that allow an entirely new approach to the computerized perception of data. These so-called connectionist models are inspired by what is known about the architecture of biological neurons, in which the "intelligence" or processing capability of the network is a result of the interconnection strengths between large arrays of nonlinear processing nodes. Neural networks are described and then are used to analyze the common radiological problem of pattern recognition on a noisy background. Classical signal detection theory is used to compare network performance against that of human observers, using computer-generated sets of very simple "nodules." The neural network performed with better accuracy, relative to human observer performance, in the detection of this elementary test object. Although these results may not scale up with more complex images, the favorable performance of neural networks at this level suggests that further investigation is warranted.

Artificial Intelligence↗
PubMed2003

Theoretical note: simulating latent inhibition with selection neural networks.

The selection neural-network model proposed by Donahoe et al. [J. Exp. Anal. Behav. 60 (1993) 17] was used to simulate latent inhibition (LI). The model can simulate increases of LI by the number, intensity, and duration of preexposed conditioned stimulus (CS). It can also simulate dependence on total CS preexposure time, CS specificity, and attenuation by preexposure to a compound that includes the to-be-trained CS. It also predicts a potentially new phenomenon: acquisition facilitation by preexposure to a stimulus that is orthogonal to and synaptically competitive with the to-be-trained CS. The basic mechanism is the same through which the model simulates extinction, namely, weight decrement. The realization of this mechanism in the present simulations required two conditions. First, networks had to come to the experimental situation with substantial initial connection weights in the sensory-association subnetwork (0.15, compared to the 0.01 value we have used in all previous simulations). Second, the discrepancy threshold for deciding whether to increase or decrease weights had to be larger than zero (the value we have used in all published simulations). A value of 0.001 was sufficient to produce all the effects.

Journal Article↗
PubMed1986

Sequential state generation by model neural networks.

Sequential patterns of neural output activity form the basis of many biological processes, such as the cyclic pattern of outputs that control locomotion. I show how such sequences can be generated by a class of model neural networks that make defined sets of transitions between selected memory states. Sequence-generating networks depend upon the interplay between two sets of synaptic connections. One set acts to stabilize the network in its current memory state, while the second set, whose action is delayed in time, causes the network to make specified transitions between the memories. The dynamic properties of these networks are described in terms of motion along an energy surface. The performance of the networks, both with intact connections and with noisy or missing connections, is illustrated by numerical examples. In addition, I present a scheme for the recognition of externally generated sequences by these networks.

Artificial Intelligence↗
PubMed2001

Macroscopic dynamics in separable neural networks.

Parallel dynamics of neural networks with separable coupling is given starting from Coolen-Sherrington theory. Away from saturation, it is shown that this parallel retrieve dynamics is equivalent to the sequential dynamics for finite temperature. But the finite-size effects were found to be governed by a homogeneous Markov process, not by a time-dependent Ornstein-Uhlenbeck process in sequential dynamics.

Biophysics↗
PubMed2001

A neural network architecture for data classification.

This article aims at showing an architecture of neural networks designed for the classification of data distributed among a high number of classes. A significant gain in the global classification rate can be obtained by using our architecture. This latter is based on a set of several little neural networks, each one discriminating only two classes. The specialization of each neural network simplifies their structure and improves the classification. Moreover, the learning step automatically determines the number of hidden neurons. The discussion is illustrated by tests on databases from the UCI machine learning database repository. The experimental results show that this architecture can achieve a faster learning, simpler neural networks and an improved performance in classification.

Computer Systems↗