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 469 records · Page 26Linked to original sources

PubMed1995

Learning in recurrent finite difference networks.

A recurrent learning algorithm based on a finite difference discretization of continuous equations for neural networks is derived. This algorithm has the simplicity of discrete algorithms while retaining some essential characteristics of the continuous equations. In discrete networks learning smooth oscillations is difficult if the period of oscillation is too large. The network either grossly distorts the waveforms or is unable to learn at all. We show how the finite difference formulation can explain and overcome this problem. Formulas for learning time constants and time delays in this framework are also presented.

Algorithms↗

PubMed2004

Using artificially generated spectral data to improve protein secondary structure prediction from Fourier transform infrared spectra of proteins.

Secondary structures of proteins have been predicted using neural networks from their Fourier transform infrared spectra. To improve the generalization ability of the neural networks, the training data set has been artificially increased by linear interpolation. The leave-one-out approach has been used to demonstrate the applicability of the method. Bayesian regularization has been used to train the neural networks and the predictions have been further improved by the maximum-likelihood estimation method. The networks have been tested and standard error of prediction (SEP) of 4.19% for alpha helix, 3.49% for beta sheet, and 3.15% for turns have been achieved. The results indicate that there is a significant decrease in the SEP for each type of structure parameter compared to previous works.

Algorithms↗

PubMed1997

Marr's theory of the neocortex as a self-organizing neural network.

Marr's proposal for the functioning of the neocortex (Marr, 1970) is the least known of his various theories for specific neural circuitries. He suggested that the neocortex learns by self-organization to extract the structure from the patterns of activity incident upon it. He proposed a feedforward neural network in which the connections to the output cells (identified with the pyramidal cells of the neocortex) are modified by a mechanism of competitive learning. It was intended that each output cell comes to be selective for the input patterns from a different class and is able to respond to new patterns from the same class that have not been seen before. The learning rule that Marr proposed was underspecified, but a logical extension of the basic idea results in a synaptic learning rule in which the total amount of synaptic strength of the connections from each input ("presynaptic") cell is kept at a constant level. In contrast, conventional competitive learning involves rules of the "postsynaptic" type. The network learns by exploiting the structure that Marr assumed to exist within the ensemble of input patterns. For this case, analysis is possible that extends that carried out by Marr, which was restricted to the binary classification task. This analysis is presented here, together with results from computer simulations of different types of competitive learning mechanisms. The presynaptic mechanism is best known in the computational neuroscience literature. In neural network applications, it may be a more suitable mechanism of competitive learning than those normally considered.

Algorithms↗

PubMed1998

Neural network approach for Compton-scattering imaging.

The problem of image reconstruction with Compton-scattering spectral data is an ill-posed problem, and the measurement error may be seriously amplified in the reconstruction result. For a stable solution, some kinds of a priori models of the problem should be incorporated into the process of reconstruction. Lee et al. [IEEE. Trans. Nucl. Sci. 40, 2049 (1993)] have proposed a continuous model with binary line processes. Owing to the coexistence of the continuous variable and the binary variable, the commonly used optimization methods for problems with continuous variables cannot be used in this case, and therefore a coupled-gradient artificial neutral network was proposed for this mixed-integer problem. By introducing two interacting parts (with one part for the continuous variable and the other for the binary line processes) into the network, and by defining the appropriate energy function and dynamics, high-quality solutions were obtained upon convergence of the dynamics. Some simulated results are presented.

Algorithms↗

PubMed2001

Application of neural networks to the classification of pancreatic intraductal proliferative lesions.

The aim of the study was to test applycability of neural networks to classification of pancreatic intraductal proliferative lesions basing on nuclear features, especially chromatin texture. Material for the study was obtained from patients operated on for pancreatic cancer, chronic pancreatitis and other tumours requiring pancreatic resection. Intraductal lesions were classified as low and high grade as previously described. The image analysis system consisted of a microscope, CCD camera combined with a PC and AnalySIS v. 2.11 software. The following texture characteristics were measured: variance of grey levels, features extracted from the grey levels correlation matrix and mean values, variance and standard deviation of the energy obtained from Laws matrices. Furthermore we used moments derived invariants and basic geometric data such as surface area, the minimum and maximum diameter and shape factor. The sets of data were randomly divided into training and testing groups. The training of the network using the back-propagation algorithm, and the final classification of data was carried out with a neural network simulator SNNS v. 4.1. We studied the efficacy of networks containing from one to three hidden layers. Using the best network, containing three hidden layers, the rate of correct classification of nuclei was 73%, and the rate of misdiagnosis was 3%; in 24% the network response was ambiguous. The present findings may serve as a starting point in search for methods facilitating early diagnosis of ductal pancreatic carcinoma.

Adenocarcinoma↗

PubMed1998

A neural network approach to the rapid computation of rotational correlation times from slow motional ESR spectra.

We explore the use of feed forward artificial neural networks for determining rotational correlation times from slow motional nitroxide electron spin resonance spectra. This approach is rapid and potentially eliminates the need for traditional iterative fitting procedures. Two networks are examined: the radial basis network and the multilayer perceptron. Although the radial basis network trains rapidly and performs well on simulated spectra, it is less satisfactory when applied to experimental spectra. In contrast, the multilayer perceptron trains slowly but is excellent at extracting correlation times from experimental spectra. In addition, the multilayer perceptron operates well in the presence of noise as long as the signal-to-noise ratio is greater than approximately 200/1. These findings suggest neural networks offer a promising approach for rapidly extracting correlation times without the need for iterative simulations.

Electron Spin Resonance Spectroscopy↗

PubMed2004

Multi-layered greedy network-growing algorithm: extension of greedy network-growing algorithm to multi-layered networks.

In this paper, we extend our greedy network-growing algorithm to multi-layered networks. With multi-layered networks, we can solve many complex problems that single-layered networks fail to solve. In addition, the network-growing algorithm is used in conjunction with teacher-directed learning that produces appropriate outputs without computing errors between targets and outputs. Thus, the present algorithm is a very efficient network-growing algorithm. The new algorithm was applied to three problems: the famous vertical-horizontal lines detection problem, a medical data problem and a road classification problem. In all these cases, experimental results confirmed that the method could solve problems that single-layered networks failed to. In addition, information maximization makes it possible to extract salient features in input patterns.

Algorithms↗

PubMed2006

Detecting and sorting targeting peptides with neural networks and support vector machines.

This paper presents a composite multi-layer classifier system for predicting the subcellular localization of proteins based on their amino acid sequence. The work is an extension of our previous predictor PProwler v1.1 which is itself built upon the series of predictors SignalP and TargetP. In this study we outline experiments conducted to improve the classifier design. The major improvement came from using Support Vector machines as a "smart gate" sorting the outputs of several different targeting peptide detection networks. Our final model (PProwler v1.2) gives MCC values of 0.873 for non-plant and 0.849 for plant proteins. The model improves upon the accuracy of our previous subcellular localization predictor (PProwler v1.1) by 2% for plant data (which represents 7.5% improvement upon TargetP).

Amino Acid Sequence↗

PubMed2000

Radical pruning: a method to construct skeleton radial basis function networks.

Trained radial basis function networks are well-suited for use in extracting rules and explanations because they contain a set of locally tuned units. However, for rule extraction to be useful, these networks must first be pruned to eliminate unnecessary weights. The pruning algorithm cannot search the network exhaustively because of the computational effort involved. It is shown that using multiple pruning methods with smart ordering of the pruning candidates, the number of weights in a radial basis function network can be reduced to a small fraction of the original number. The complexity of the pruning algorithm is quadratic (instead of exponential) in the number of network weights. Pruning performance is shown using a variety of benchmark problems from the University of California, Irvine machine learning database.

Algorithms↗

PubMed1993

A hardware efficient cascadable chip set for ANN's with on-chip backpropagation.

In this paper, an analogue, cascadable, CMOS chip set for artificial neural networks is presented. The chip set (a synapse chip and a neuron chip) offer on-chip back-propagation learning in a fully parallel, layered, feedforward network of arbitrary size and topology. The learning scheme is implemented with no extra circuits at the synapse sites (compared to the system without the learning scheme) and extra circuits of a complexity only about the same as the neurons at the neuron sites. Also, no additional wiring is required by the learning scheme. Measurements on an experimental chip set are presented.

Algorithms↗

PubMed2005

Restoring partly occluded patterns: a neural network model.

This paper proposes a neural network model that has an ability to restore missing portions of partly occluded patterns. It is a multi-layered hierarchical neural network, in which visual information is processed by interaction of bottom-up and top-down signals. Memories of learned patterns are stored in the connections between cells. Occluded parts of a pattern are reconstructed mainly by top-down signals from higher stages of the network, while the unoccluded parts are reproduced mainly by signals from lower stages. The restoration progresses successfully, even if the occluded pattern is a deformed version of a learned pattern. The model tries to complete even an unlearned pattern by interpolating and extrapolating visible edges. Resemblance of local features to other learned patterns are also utilized for the restoration.

Algorithms↗

PubMed1997

[Micro-particle image processing based on an artificial neuron network with fluid properties].

The form of macro-particle is a close successive region in two-valued micro-particle image, and the detection of microparticles is actually that of close successive regions. Accordign to this theory, this paper present a new technique for micro-particles detecting based on an artificial neuron network modeled on the diffusing behaviour of real visual system, which has fluid properties. The results of simulation on computer shew that this method is very effect.

Blood Cell Count↗

PubMed2006

Pruning and model-selecting algorithms in the RBF frameworks constructed by support vector learning.

This paper presents the pruning and model-selecting algorithms to the support vector learning for sample classification and function regression. When constructing RBF network by support vector learning we occasionally obtain redundant support vectors which do not significantly affect the final classification and function approximation results. The pruning algorithms primarily based on the sensitivity measure and the penalty term. The kernel function parameters and the position of each support vector are updated in order to have minimal increase in error, and this makes the structure of SVM network more flexible. We illustrate this approach with synthetic data simulation and face detection problem in order to demonstrate the pruning effectiveness.

Algorithms↗

PubMed2005

Smooth function approximation using neural networks.

An algebraic approach for representing multidimensional nonlinear functions by feedforward neural networks is presented. In this paper, the approach is implemented for the approximation of smooth batch data containing the function's input, output, and possibly, gradient information. The training set is associated to the network adjustable parameters by nonlinear weight equations. The cascade structure of these equations reveals that they can be treated as sets of linear systems. Hence, the training process and the network approximation properties can be investigated via linear algebra. Four algorithms are developed to achieve exact or approximate matching of input-output and/or gradient-based training sets. Their application to the design of forward and feedback neurocontrollers shows that algebraic training is characterized by faster execution speeds and better generalization properties than contemporary optimization techniques.

Algorithms↗

PubMed2001

The constraint based decomposition (CBD) training architecture.

The Constraint Based Decomposition (CBD) is a constructive neural network technique that builds a three or four layer network, has guaranteed convergence and can deal with binary, n-ary, class labeled and real-value problems. CBD is shown to be able to solve complicated problems in a simple, fast and reliable manner. The technique is further enhanced by two modifications (locking detection and redundancy elimination) which address the training speed and the efficiency of the internal representation built by the network. The redundancy elimination aims at building more compact architectures while the locking detection aims at improving the training speed. The computational cost of the redundancy elimination is negligible and this enhancement can be used for any problem. However, the computational cost of the locking detection is exponential in the number of dimensions and should only be used in low dimensional spaces. The experimental results show the performance of the algorithm presented in a series of classical benchmark problems including the 2-spiral problem and the Iris, Wine, Glass, Lenses, Ionosphere, Lung cancer, Pima Indians, Bupa, TicTacToe, Balance and Zoo data sets from the UCI machine learning repository. CBD's generalization accuracy is compared with that of C4.5, C4.5 with rules, incremental decision trees, oblique classifiers, linear machine decision trees, CN2, learning vector quantization (LVQ), backpropagation, nearest neighbor, Q* and radial basis functions (RBFs). CBD provides the second best average accuracy on the problems tested as well as the best reliability (the lowest standard deviation).

Algorithms↗

PubMed1996

The enteric neural network and three dimensional computer modelling of intestinal peristalsis.

A computer model of the enteric nervous system has been developed using MATLAB in order to determine the extent to which the nature of intestinal activity can be explained by our current understanding of the projections and connectivity of enteric neurons. The model is based on repeated, identical overlapping modules, each of which contains the same number of neurones and circular muscle. The connections between modules were derived from microanatomical data. This simple model explains some characteristic features of the generation of an intestinal motor pattern.

Animals↗

PubMed2004

Prediction of left ventricular ejection fraction in patients with coronary artery disease based on an analysis of perfusion patterns at rest. Assessment by an artificial neural network.

BACKGROUND: In CAD, left ventricular function depends on the condition of myocardial perfusion, hence it may be presumed that blood flow abnormalities may enable the LVEF to be predicted. The aim of the study was to apply an Artificial Neural Network (ANN) to investigate the relationships between myocardial perfusion and LVEF, measured simultaneously. MATERIAL AND METHODS: gSPECT examinations were performed in 95 patients with CAD, divided into training (n = 50) and testing (n = 45) groups. using the acquired data, in each subject the LVEF was calculated and a perfusion polar map was constructed and divided into 25 segments. Based on results obtained in the training group, a characteristic configuration of segments was defined, with features enabling differentiation between the individual subjects of that group. The set of those segments, as well as the corresponding LVEF values enabled the optimum network architecture to be constructed and trained. The trained ANN was verified by application to the testing group. RESULTS: Using the above-described procedure, 15 polar map segments were defined which enabled the patients of the training group to be differentiated sufficiently enough to make their further recognition possible. The optimal network structure consisting 25 neurons was obtained by comparing the activity in those segments in individual subjects with corresponding LVEF values. Based on the above model, the obtained network was able to reproduce learning data (r = 0.832; learning error = 4.84%) and to apply the gained knowledge to the testing cases (r = 0.786; testing error = 4.99%). CONCLUSIONS: The obtained network can generalise learned information. To predict LVEF, some polar map segments should be excluded from the analysis. Erroneous LVEF prediction may occur resulting mainly from conditions independent from perfusion abnormalities.

Artificial Intelligence↗

PubMed2003

Novel neutral network approach to call admission control in high-speed networks.

This paper presents a novel Call Admission Control (CAC) scheme which adopts the neural network approach, namely Minimal Resource Allocation Network (MRAN) and its extended version EMRAN. Though the current focus is on the Call Admission Control (CAC) for Asynchronous Transfer Mode (ATM) networks, the scheme is applicable to most high-speed networks. As there is a need for accurate estimation of the required bandwidth for different services, the proposed scheme can offer a simple design procedure and provide a better control in fulfilling the Quality of Service (QoS) requirements. MRAN and EMRAN are on-line learning algorithms to facilitate efficient admission control in different traffic environments. Simulation results show that the proposed CAC schemes are more efficient than the two conventional CAC approaches, the Peak Bandwidth Allocation scheme and the Cell Loss Ratio (CLR) upperbound formula scheme. The prediction precision and computational time of MRAN and EMRAN algorithms are also investigated. Both MRAN and EMRAN algorithms yield similar performance results, but the EMRAN algorithm has less computational load.

Algorithms↗