Modular neural networks.
Explore the source record for details and available documents.
Computer Systems↗
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.
Improving generalization capabilities of dynamic neural networks.
This work addresses the problem of improving the generalization capabilities of continuous recurrent neural networks. The learning task is transformed into an optimal control framework in which the weights and the initial network state are treated as unknown controls. A new learning algorithm based on a variational formulation of Pontrayagin's maximum principle is proposed. Under reasonable assumptions, its convergence is discussed. Numerical examples are given that demonstrate an essential improvement of generalization capabilities after the learning process of a dynamic network.
Algorithms↗
Activity patterns in a model for the subthalamopallidal network of the basal ganglia.
Based on recent experimental data, we have developed a conductance-based computational network model of the subthalamic nucleus and the external segment of the globus pallidus in the indirect pathway of the basal ganglia. Computer simulations and analysis of this model illuminate the roles of the coupling architecture of the network, and associated synaptic conductances, in modulating the activity patterns displayed by this network. Depending on the relationships of these coupling parameters, the network can support three general classes of sustained firing patterns: clustering, propagating waves, and repetitive spiking that may show little regularity or correlation. Each activity pattern can occur continuously or in discrete episodes. We characterize the mechanisms underlying these rhythms, as well as the influence of parameters on details such as spiking frequency and wave speed. These results suggest that the subthalamopallidal circuit is capable both of correlated rhythmic activity and of irregular autonomous patterns of activity that block rhythmicity. Increased striatal input to, and weakened intrapallidal inhibition within, the indirect pathway can switch the behavior of the circuit from irregular to rhythmic. This may be sufficient to explain the emergence of correlated oscillatory activity in the subthalamopallidal circuit after destruction of dopaminergic neurons in Parkinson's disease and in animal models of parkinsonism.
Action Potentials↗
Learning lateral interactions for feature binding and sensory segmentation from prototypic basis interactions.
We present a hybrid learning method bridging the fields of recurrent neural networks, unsupervised Hebbian learning, vector quantization, and supervised learning to implement a sophisticated image and feature segmentation architecture. This architecture is based on the competitive layer model (CLM), a dynamic feature binding model, which is applicable on a wide range of perceptual grouping and segmentation problems. A predefined target segmentation can be achieved as attractor states of this linear threshold recurrent network, if the lateral weights are chosen by Hebbian learning. The weight matrix is given by the correlation matrix of special pattern vectors with a structure dependent on the target labeling. Generalization is achieved by applying vector quantization on pair-wise feature relations, like proximity and similarity, defined by external knowledge. We show the successful application of the method to a number of artifical test examples and a medical image segmentation problem of fluorescence microscope cell images.
Image Processing, Computer-Assisted↗
A computational tool to simulate correlated activity in neural circuits.
A new computational approach to study correlated neural activity is presented. Simulating Elementary Neural NEtworks for Correlation Analysis (SENNECA) is a specific-purpose simulator oriented to small circuits of realistic neurons. The model neuron that it implements can reproduce a wide scope of integrate-and-fire models by simply adjusting the parameter set. Three different distributions of SENNECA are available: an easy-to-use web-based version, a Matlab (Windows and Linux) script, and a C++ class library for low-level coding. The main features of the simulator are explained, and several examples of neural activity analysis are given to illustrate the potential of this new tool.
Animals↗
Sparse distributed memory using N-of-M codes.
An analysis is presented of a sparse distributed memory (SDM) inspired by that described by Kanerva [Kanerva, P. (1988). Sparse distributed memory. Cambridge, MA: MIT Press] but modified to facilitate an implementation based on spiking neurons. The memory presented here employs sparse binary N-of-M codes, unipolar binary synaptic weights and a simple Hebbian learning rule. It is a two-layer network, the first (fixed) layer being similar to the 'address decoder' in Jaeckel's [Jaeckel, L.A. (1989). A class of designs for a sparse distributed memory. RIACS Technical Report 89.30, NASA Ames Research Centre] 'hyperplane' variant of Kanerva's SDM and the second (writeable) 'data store' layer being a correlation matrix memory as first proposed by Willshaw et al. [Willshaw, D. J., Buneman, O.P., & Longuet-Higgins, H.C. (1969). Non-holographic associative memory. Nature, 222, 960-962]. The resulting network is shown to have good storage efficiency and is scalable. The analysis is supported by numerical simulations and gives results that enable the configuration of the memory to be optimised for a range of noiseless and noisy environments.
Association Learning↗
Adaptability and diversity in simulated turn-taking behavior.
Turn-taking behavior is simulated in a coupled-agents system. Each agent is modeled as a mobile robot with two wheels. A recurrent neural network is used to produce the motor outputs and to hold the internal dynamics. Agents are developed to take turns on a two-dimensional arena by causing the network structures to evolve. Turn taking is established using either regular or chaotic behavior of the agents. It is found that chaotic turn takers are more sensitive in response to inputs from the other agent. Conversely, regular turn takers are comparatively robust against noisy inputs, owing to their restricted dynamics. From many observations, including turn taking with virtual agents, we claim that there is a complementary relationship between robustness and adaptability. Furthermore, by investigating the recoupling of agents from different GA generations, we report the emergence of a new turn-taking behavior. Potential for synthesizing a new form of interaction is another characteristic of chaotic turn takers.
Algorithms↗
Artificial neural networks for recognition of electrocardiographic lead reversal.
Misplacement of electrodes during the recording of an electrocardiogram (ECG) can cause an incorrect interpretation, misdiagnosis, and subsequent lack of proper treatment. The purpose of this study was twofold: (1) to develop artificial neural networks that yield peak sensitivity for the recognition of right/left arm lead reversal at a very high specificity; and (2) to compare the performances of the networks with those of 2 widely used rule-based interpretation programs. The study was based on 11,009 ECGs recorded in patients at an emergency department using computerized electrocardiographs. Each of the ECGs was used to computationally generate an ECG with right/left arm lead reversal. Neural networks were trained to detect ECGs with right/left arm lead reversal. Different networks and rule-based criteria were used depending on the presence or absence of P waves. The networks and the criteria all showed a very high specificity (99.87% to 100%). The neural networks performed better than the rule-based criteria, both when P waves were present (sensitivity 99.1%) or absent (sensitivity 94.5%). The corresponding sensitivities for the best criteria were 93.9% and 39.3%, respectively. An estimated 300 million ECGs are recorded annually in the world. The majority of these recordings are performed using computerized electrocardiographs, which include algorithms for detection of right/left arm lead reversals. In this study, neural networks performed better than conventional algorithms and the differences in sensitivity could result in 100,000 to 400,000 right/left arm lead reversals being detected by networks but not by conventional interpretation programs.
Algorithms↗
Neural networks for process control and optimization: two industrial applications.
The two most widely used neural models, multilayer perceptron (MLP) and radial basis function network (RBFN), are presented in the framework of system identification and control. The main steps for building such nonlinear black box models are regressor choice, selection of internal architecture, and parameter estimation. The advantages of neural network models are summarized: universal approximation capabilities, flexibility, and parsimony. Two applications are described in steel industry and water treatment, respectively, the control of alloying process in a hot dipped galvanizing line and the control of a coagulation process in a drinking water treatment plant. These examples highlight the interest of neural techniques, when complex nonlinear phenomena are involved, but the empirical knowledge of control operators can be learned.
Algorithms↗
Random neural networks with state-dependent firing neurons.
This letter studies the properties of the random neural networks (RNNs) with state-dependent firing neurons. It is assumed that the times between successive signal emissions of a neuron are dependent on the neuron potential. Under certain conditions, the networks keep the simple product form of stationary solutions and exhibit enhanced capacity of adjusting the probability distribution of the neuron states. It is demonstrated that desired associative memory states can be stored in the networks.
Action Potentials↗
Combining geometric and probabilistic reasoning for computer-based penetrating-trauma assessment.
OBJECTIVE: To ascertain whether three-dimensional geometric and probabilistic reasoning methods can be successfully combined for computer-based assessment of conditions arising from ballistic penetrating trauma to the chest and abdomen. DESIGN: The authors created a computer system (TraumaSCAN) that integrates three-dimensional geometric reasoning about anatomic likelihood of injury with probabilistic reasoning about injury consequences using Bayesian networks. Preliminary evaluation of TraumaSCAN was performed via a retrospective study testing performance of the system on data from 26 cases of actual gunshot wounds. MEASUREMENTS: Areas under the receiver operating characteristics (ROC) curve were calculated for each condition modeled in TraumaSCAN that was present in the 26 cases. The comprehensiveness and relevance of the TraumaSCAN diagnosis for the 26 cases were used to assess the overall performance of the system. To test the ability of TraumaSCAN to handle limited findings, these measurements were calculated both with and without input of observed findings into the Bayesian network. RESULTS: For the 11 conditions assessed, the worst area under the ROC curve with no observed findings input into the Bayesian network was 0.542 (95% CI, 0.146-0.937), the median was 0.883 (95% CI, 0.713-1.000), and the best was 1.00 (95% CI, 1.000-1.000). The worst area under the ROC curve with all observed findings input into the Bayesian network was 0.835 (95% CI, 0.602-1.000), the median was 0.941 (95% CI, 0.827-1.000), and the best was 0.992 (95% CI, 0.965-1.000). A comparison of the areas under the curve obtained with and without input of observed findings into the Bayesian network showed that there were significant differences for 2 of the 11 conditions assessed. CONCLUSION: A computer-based method that combines geometric and probabilistic reasoning shows promise as a tool for assessing ballistic penetrating trauma to the chest and abdomen.
Bayes Theorem↗
Functional network topology learning and sensitivity analysis based on ANOVA decomposition.
A new methodology for learning the topology of a functional network from data, based on the ANOVA decomposition technique, is presented. The method determines sensitivity (importance) indices that allow a decision to be made as to which set of interactions among variables is relevant and which is irrelevant to the problem under study. This immediately suggests the network topology to be used in a given problem. Moreover, local sensitivities to small changes in the data can be easily calculated. In this way, the dual optimization problem gives the local sensitivities. The methods are illustrated by their application to artificial and real examples.
Analysis of Variance↗
Application of a bi-directional associative memory (BAM) network in computer assisted learning in chemistry.
A computer assisted learning software based on a bi-directional associative memory (BAM) network was developed. The software was implemented to assist students in associating the names of the elements in the periodic table with their chemical symbols. The use of the BAM facilitates the analysis and interpretation of students' responses. The software package can be modified easily as an educational tool for other disciplines.
Algorithms↗
Evaluation of simplified compartmental models of reconstructed neocortical neurons for use in large-scale simulations of biological neural networks.
The electrotonic properties of the complex arborizations of neurons can be simulated by creating compartmental models based on the morphology of real neurons. These models can be very detailed with thousands of individual compartments and active channels. Large numbers of these models can be linked together into biologically realistic, large-scale neural networks with which to obtain a better understanding of the interactions among real neurons. However, the use of detailed compartmental models in such large networks is hindered by long computation times. Methods exist to reduce the complex morphology of detailed compartmental models to simpler reconstructions that retain many of the electrotonic properties of the original model yet are computationally efficient. However, little work exists that evaluates the limitations and performance of such reduced models with realistic active conductances modeled in both the soma and the dendrites to ensure that they are appropriate for use in biologically realistic network models. We have created detailed and reduced models of reconstructed dye-filled neurons from rat somatosensory neocortex and evaluated the ability of the reduced models to faithfully reproduce the input-output functions of the more detailed models. We find that the reduced models are not capable of perfectly reproducing the exact output of the detailed models using identical parameters. However, if the parameters are adjusted the reduced models are certainly capable of providing input-output patterns that are well within an acceptable range of known neural activity. The limitations and the benefits of such models are discussed.
Animals↗
Optimal competitive hopfield network with stochastic dynamics for maximum cut problem.
In this paper, introducing stochastic dynamics into an optimal competitive Hopfield network model (OCHOM), we propose a new algorithm that permits temporary energy increases which helps the OCHOM escape from local minima. The goal of the maximum cut problem, which is an NP-complete problem, is to partition the node set of an undirected graph into two parts in order to maximize the cardinality of the set of edges cut by the partition. The problem has many important applications including the design of VLSI circuits and design of communication networks. Recently, Galán-Marín et al. proposed the OCHOM, which can guarantee convergence to a global/local minimum of the energy function, and performs better than the other competitive neural approaches. However, the OCHOM has no mechanism to escape from local minima. The proposed algorithm introduces stochastic dynamics which helps the OCHOM escape from local minima, and it is applied to the maximum cut problem. A number of instances have been simulated to verify the proposed algorithm.
Algorithms↗
A computational framework for cortical learning.
Recent physiological findings have revealed that long-term adaptation of the synaptic strengths between cortical pyramidal neurons depends on the temporal order of presynaptic and postsynaptic spikes, which is called spike-timing-dependent plasticity (STDP) or temporally asymmetric Hebbian (TAH) learning. Here I prove by analytical means that a physiologically plausible variant of STDP adapts synaptic strengths such that the presynaptic spikes predict the postsynaptic spikes with minimal error. This prediction error model of STDP implies a mechanism for cortical memory: cortical tissue learns temporal spike patterns if these spike patterns are repeatedly elicited in a set of pyramidal neurons. The trained network finishes these patterns if their beginnings are presented, thereby recalling the memory. Implementations of the proposed algorithms may be useful for applications in voice recognition and computer vision.
Action Potentials↗
Comparison of different calibration methods for the determination by FT-NIR spectroscopy of the hydroxyl number in polyester resins.
Different calibration methods have been applied for the determination of the Hydroxyl Number in polyester resins, namely Partial Least Squares (PLS), Principal Component Regression (PCR), Ordinary Least Squares with selection of the variables by genetic algorithm (OLS-GEN) and back-propagation Artificial Neural Networks (BP-ANN). The predictive ability of the regression models was estimated by splitting the dataset in training and test sets by application of the Kohonen self-organising maps. The linear methods (OLS-GEN, PLS and PCR) showed comparable results while artificial neural networks provided the best results both in fitting and prediction.
Calibration↗
Ensembles of radial basis function networks for spectroscopic detection of cervical precancer.
The mortality related to cervical cancer can be substantially reduced through early detection and treatment. However, current detection techniques, such as Pap smear and colposcopy, fail to achieve a concurrently high sensitivity and specificity. In vivo fluorescence spectroscopy is a technique which quickly, noninvasively and quantitatively probes the biochemical and morphological changes that occur in precancerous tissue. A multivariate statistical algorithm was used to extract clinically useful information from tissue spectra acquired from 361 cervical sites from 95 patients at 337-, 380-, and 460-nm excitation wavelengths. The multivariate statistical analysis was also employed to reduce the number of fluorescence excitation-emission wavelength pairs required to discriminate healthy tissue samples from precancerous tissue samples. The use of connectionist methods such as multilayered perceptrons, radial basis function (RBF) networks, and ensembles of such networks was investigated. RBF ensemble algorithms based on fluorescence spectra potentially provide automated and near real-time implementation of precancer detection in the hands of nonexperts. The results are more reliable, direct, and accurate than those achieved by either human experts or multivariate statistical algorithms.
Algorithms↗