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 469 records · Page 26Linked to original sources
PubMed1992

Differential features for a neural network based anesthesia alarm system.

We have developed a neural network based alarm system that identifies 19 specific faults in the anesthesia breathing circuit, such as "Inspiratory Hose Leak," or "Y-Piece Disconnection." CO2, pressure, and expired flow waveforms, along with ventilator settings, were sampled by a personal computer. Fifty-two features, such as "maximum CO2" or "minimum pressure", were extracted from each breath, converted to "differential" features, normalized, and used as the inputs of a three layered feed-forward neural network. The network was trained, using backward error propagation with momentum, to classify each breath as normal or containing one of 19 faults. To collect the neutral network training set, seven dogs were anesthetized and ventilated using controlled ventilation. Each of 19 faults were created over a range of ventilator settings and fresh gas flows. The neural network correctly identified 83.1% of 550 events presented to it during testing. These preliminary results are an encouraging example of neural network applications in the field of clinical monitoring.

Anesthesia, Closed-Circuit↗
PubMed1993

Prediction of protein secondary structures by a neural network.

We have studied the prediction of globular protein secondary structures by neural networks. Protein secondary structures are allocated to amino acid residues using Kabsch and Sander's dictionary of protein secondary structures and the neural network is taught the protein secondary structures. The input layer of the neural network allows sequences of residues including 20 amino acids, chain break, B, X and Z. We consider classifying secondary structures into groups of 3, 4 and 8. In each case, we calculate the percentage of correct predictions. We discuss the effect of overlearning on the protein secondary structure prediction. In addition, we include the application of a neural network with a modular architecture to prediction of protein secondary structures. We compare the results from neural networks with a modular architecture and with a simple three-layer structure.

Algorithms↗
PubMed2005

Global exponential stability and global convergence in finite time of delayed neural networks with infinite gain.

This paper introduces a general class of neural networks with arbitrary constant delays in the neuron interconnections, and neuron activations belonging to the set of discontinuous monotone increasing and (possibly) unbounded functions. The discontinuities in the activations are an ideal model of the situation where the gain of the neuron amplifiers is very high and tends to infinity, while the delay accounts for the finite switching speed of the neuron amplifiers, or the finite signal propagation speed. It is known that the delay in combination with high-gain nonlinearities is a particularly harmful source of potential instability. The goal of this paper is to single out a subclass of the considered discontinuous neural networks for which stability is instead insensitive to the presence of a delay. More precisely, conditions are given under which there is a unique equilibrium point of the neural network, which is globally exponentially stable for the states, with a known convergence rate. The conditions are easily testable and independent of the delay. Moreover, global convergence in finite time of the state and output is investigated. In doing so, new interesting dynamical phenomena are highlighted with respect to the case without delay, which make the study of convergence in finite time significantly more difficult. The obtained results extend previous work on global stability of delayed neural networks with Lipschitz continuous neuron activations, and neural networks with discontinuous neuron activations but without delays.

Algorithms↗
PubMed1998

A dynamic neural network with temporal coding and functional connectivity.

A neural network model capable of altering its pattern classifying properties by program input is proposed. Here the "program input" is another source of input besides the pattern input. Unlike most neural network models, this model runs as a deterministic point process of spikes in continuous time; connections among neurons have finite delays, which are set randomly according to a normal distribution. Furthermore, this model utilizes functional connectivity which is dynamic connectivity among neurons peculiar to temporal-coding neural networks with short neuronal decay time constants. Computer simulation of the proposed network has been performed, and the results are considered in light of experimental results shown recently for correlated firings of neurons.

Computer Simulation↗
PubMed2000

An efficient neural network approach to dynamic robot motion planning.

In this paper, a biologically inspired neural network approach to real-time collision-free motion planning of mobile robots or robot manipulators in a nonstationary environment is proposed. Each neuron in the topologically organized neural network has only local connections, whose neural dynamics is characterized by a shunting equation. Thus the computational complexity linearly depends on the neural network size. The real-time robot motion is planned through the dynamic activity landscape of the neural network without any prior knowledge of the dynamic environment, without explicitly searching over the free workspace or the collision paths, and without any learning procedures. Therefore it is computationally efficient. The global stability of the neural network is guaranteed by qualitative analysis and the Lyapunov stability theory. The effectiveness and efficiency of the proposed approach are demonstrated through simulation studies.

Artificial Intelligence↗
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↗
PubMed2000

Neural network modeling of risk assessment in child protective services.

The advantages of using neural network methodology for the modeling of complex social science data are demonstrated, and neural network analysis is applied to Washington State Child Protective Services risk assessment data. Neural network modeling of the association between social worker overall assessment of risk and the 37 separate risk factors from the State of Washington Risk Assessment Matrix is shown to provide case classification results superior to linear or logistic multiple regression. The improvement in case prediction and classification accuracy is attributed to the superiority of neural networks for modeling nonlinear relationships between interacting variables; in this respect the mathematical framework of neural networks is a better approximation to the actual process of human decision making than linear, main effects regression. The implications of this modeling advantage for evaluating social science data within the framework of ecological theories are discussed.

Child↗
PubMed1998

Multilayer neural networks and Bayes decision theory.

There are many applications of multilayer neural networks to pattern classification problems in the engineering field. Recently, it has been shown that Bayes a posteriori probability can be estimated by feedforward neural networks through computer simulation. In this paper, Bayes decision theory is combined with the approximation theory on three-layer neural networks, and the two-category n-dimensional Gaussian classification problem is studied. First, we prove theoretically that three-layer neural networks with at least 2n hidden units have the capability of approximating the a posteriori probability in the two-category classification problem with arbitrary accuracy. Second, we prove that the input-output function of neural networks with at least 2n hidden units tends to the a posteriori probability as Back-Propagation learning proceeds ideally. These results provide a theoretical basis for the study of pattern classification by computer simulation.

Journal Article↗
PubMed2004

Prediction and identification using wavelet-based recurrent fuzzy neural networks.

This paper presents a wavelet-based recurrent fuzzy neural network (WRFNN) for prediction and identification of nonlinear dynamic systems. The proposed WRFNN model combines the traditional Takagi-Sugeno-Kang (TSK) fuzzy model and the wavelet neural networks (WNN). This paper adopts the nonorthogonal and compactly supported functions as wavelet neural network bases. Temporal relations embedded in the network are caused by adding some feedback connections representing the memory units into the second layer of the feedforward wavelet-based fuzzy neural networks (WFNN). An online learning algorithm, which consists of structure learning and parameter learning, is also presented. The structure learning depends on the degree measure to obtain the number of fuzzy rules and wavelet functions. Meanwhile, the parameter learning is based on the gradient descent method for adjusting the shape of the membership function and the connection weights of WNN. Finally, computer simulations have demonstrated that the proposed WRFNN model requires fewer adjustable parameters and obtains a smaller rms error than other methods.

Algorithms↗
PubMed1995

Theoretical results for a class of neural networks.

The ability to derive minimal network architectures for neural networks has been at the center of attention for several years now. To this date numerous algorithms have been proposed to automatically construct networks. Unfortunately, these algorithms lack a fundamental theoretical analysis of their capabilities and only empirical evaluations on a few selected benchmark problems exist. Some theoretical results have been provided for small classes of well-known benchmark problems such as parity- and encoder-functions, but these are of little value due to their restrictiveness. In this work we describe a general class of 2-layer networks with 2 hidden units capable of representing a large set of problems. The cardinality of this class grows exponentially with regard to the inputs N. Furthermore, we outline a simple algorithm that allows us to determine, if any function (problem) is a member of this class. The class considered in this paper includes the benchmark problems parity and symmetry. Finally, we expand this class to include an even larger set of functions and point out several interesting properties it exhibits.

Models, Theoretical↗
PubMed2003

Necessary and sufficient condition for absolute stability of normal neural networks.

Globally convergent dynamics of a class of neural networks with normal connection matrices is studied by using the Lyapunov function method and spectral analysis of the connection matrices. It is shown that the networks are absolutely stable if and only if all the real parts of the eigenvalues of the connection matrices are nonpositive. This extends an existing result on symmetric neural networks to a larger class including certain asymmetric networks. Further extension of the present result to certain non-normal case leads naturally to a quasi-normal matrix condition, which may be interpreted as a generalization of the so-called principle of detailed balance for the connection weights or the quasi-symmetry condition that was previously proposed in the literature in association with symmetric neural networks. These results are of particular interest in neural optimization and classification problems.

Models, Theoretical↗
PubMed1997

A constrained neural network Kalman filter for price estimation in high frequency financial data.

In this paper we present a neural network extended Kalman filter for modeling noisy financial time series. The neural network is employed to estimate the nonlinear dynamics of the extended Kalman filter. Conditions for the neural network weight matrix are provided to guarantee the stability of the filter. The extended Kalman filter presented is designed to filter three types of noise commonly observed in financial data: process noise, measurement noise, and arrival noise. The erratic arrival of data (arrival noise) results in the neural network predictions being iterated into the future. Constraining the neural network to have a fixed point at the origin produces better iterated predictions and more stable results. The performance of constrained and unconstrained neural networks within the extended Kalman filter is demonstrated on "Quote" tick data from the $/DM exchange rate (1993-1995).

Algorithms↗
PubMed1993

Using neural networks to model personality development.

A neural network approach to modeling the development of personality traits through social learning is presented. From the more general model the special case of a network mapping four situation dimensions (input neurons) into seven dimensional personality traits (output neurons) is described. This network is allowed to learn with input/output sets representing conditions suspected of leading to a borderline personality disorder. The network's ability to learn these pattern pairs is demonstrated. The trained network is then presented with new input (situational) patterns and is shown to respond to these new situations with output patterns consistent with a borderline personality disorder. The neural network model is thus shown to have important advantages over other personality models in that it can predict what situations will produce shifts in personality traits, for example from active to passive. This model provides a quantitative and reproducible framework within which to discover and test theories of personality development. It is hoped that it will extend our ability to predict human behavior.

Humans↗
PubMed1994

Classification of wheat varieties by isoelectric focusing patterns of gliadins and neural network.

Classification of wheat varieties, using isoelectric focusing patterns of the gliadins, image processing and neural networks, is described. The method was compared to a statistical classification method, discriminant analysis. The isoelectric point and the area of each band were calculated by image processing. Different methods of presenting the electrophoretic patterns to the neural network were studied. The most effective method was transformation of the electrophoretic pattern to a small (11 x 47 pixels) representation of the original digitized image, which was presented to the neural network as a vector. The neural network was trained with a number of patterns and tested with new patterns from different electrophoretic runs of the same wheat varieties. In this study we used ten different wheat varieties and the neural network was able to classify 95.5% of the patterns correctly. The statistical classification method classified the same data set 91.8% correctly. We conclude that both the neural network and discriminant analysis were able to classify the patterns correctly with a high degree of certainty. The patterns that were misclassified were indistinguishable by visual inspection.

Discriminant Analysis↗
PubMed1997

Reinforcement learning in random neural networks for cascaded decisions.

The Random Neural Network (RNN) model, in which signals travel as voltage spikes rather than as fixed signal levels, represents more closely the manner in which signals are transmitted in biophysical neural networks. In this paper a reinforcement learning strategy is proposed to make a sequence of cascaded decisions to achieve a goal while aiming to optimize the total cost of the cascaded decisions. For this purpose, RANs are used to model the system and a weight update rule together with a reinforcement function is provided. The performance of the learning strategy is analysed by applying it to the maze learning problem. The simulation results show that the performance of the system is highly dependent on the chosen reinforcement function and quite satisfactory results are obtained when the reinforcement function takes the recency effect into consideration.

Action Potentials↗
PubMed1998

Architecture of a neural network client/server system for decision support in clinical information systems.

Neural networks have demonstrated their research potential in bio-medical sciences. The literature is filled with experiments that evidence the value of neural networks for the solution of diagnostic and predictive problems. The next step is to direct research efforts toward implementation of these neural networks into the clinical information environments where their diagnostic and predictive capabilities can be truly utilized. To accomplish this goal, it is necessary to create a new generation of neural network tools that ease the transition of experimental results to a production state. This paper describes the architecture of such a system.

Decision Support Systems, Clinical↗
PubMed1991

Neural network programming in bioprocess variable estimation and state prediction.

A neural network program with efficient learning ability for bioprocess variable estimation and state prediction was developed. A 3 layer, feed-forward neural network architecture was used, and the program was written in Quick C ver 2.5 for an IBM compatible computer with a 80486/33 MHz processor. A back propagation training algorithm was used based on learning by pattern and momentum in a combination as used to adjust the connection of weights of the neurons in adjacent layers. The delta rule was applied in a gradient descent search technique to minimize a cost function equal to the mean square difference between the target and the network output. A non-linear, sigmoidal logistic transfer function was used in squashing the weighted sum of the inputs of each neuron to a limited range output. A good neural network prediction model was obtained by training with a sequence of past time course data of a typical bioprocess. The well trained neural network estimated accurately and rapidly the state variables with or without noise even under varying process dynamics.

Algorithms↗
PubMed2004

Software reliability prediction using recurrent neural network with Bayesian regularization.

A recurrent neural network modeling approach for software reliability prediction with respect to cumulative failure time is proposed. Our proposed network structure has the capability of learning and recognizing the inherent internal temporal property of cumulative failure time sequence. Further, by adding a penalty term of sum of network connection weights, Bayesian regularization is applied to our network training scheme to improve the generalization capability and lower the susceptibility of overfitting. The performance of our proposed approach has been tested using four real-time control and flight dynamic application data sets. Numerical results show that our proposed approach is robust across different software projects, and has a better performance with respect to both goodness-of-fit and next-step-predictability compared to existing neural network models for failure time prediction.

Algorithms↗