PubMed Health⌕ Search

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 1,243 records · Page 69Linked to original sources
PubMed1994

Experimental analysis of large belief networks for medical diagnosis.

We present an experimental analysis of two parameters that are important in knowledge engineering for large belief networks. We conducted the experiments on a network derived from the Internist-1 medical knowledge base. In this network, a generalization of the noisy-OR gate is used to model causal independence for the multivalued variables, and leak probabilities are used to represent the nonspecified causes of intermediate states and findings. We study two network parameters, (1) the parameter governing the assignment of probability values to the network, and (2) the parameter denoting whether the network nodes represent variables with two or more than two values. The experimental results demonstrate that the binary simplification computes diagnoses with similar accuracy to the full multivalued network. We discuss the implications of these parameters, as well other network parameters, for knowledge engineering for medical applications.

Artificial Intelligence↗
PubMed1998

Computational models of neuromodulation.

Computational modeling of neural substrates provides an excellent theoretical framework for the understanding of the computational roles of neuromodulation. In this review, we illustrate, with a large number of modeling studies, the specific computations performed by neuromodulation in the context of various neural models of invertebrate and vertebrate preparations. We base our characterization of neuromodulations on their computational and functional roles rather than on anatomical or chemical criteria. We review the main framework in which neuromodulation has been studied theoretically (central pattern generation and oscillations, sensory processing, memory and information integration). Finally, we present a detailed mathematical overview of how neuromodulation has been implemented at the single cell and network levels in modeling studies. Overall, neuromodulation is found to increase and control computational complexity.

Animals↗
PubMed1995

A parallel neural network simulator on the connection machine CM-5.

We here present a parallel implementation of artificial neural networks on the connection machine CM-5 and compare it with other parallel implementations on SIMD and MIMD architectures. This parallel implementation was developed with the goal of efficiently training large neural networks with huge training pattern sets for applications in molecular biology, in particular the prediction of coding regions in DNA sequences. The implementation uses training pattern parallelism and makes use of the parallel I/O facilities of the CM-5 and its efficient reduction operations available within the control network to achieve a high scalability. The parallel simulator obtains a maximum speed of 149.25 MCUPS for training feedforward networks with backpropagation on a 512 processor CM-5 system without using the CM-5 vector facility. The implementation poses no restriction on the type of network topology and works with different batch training algorithms like BP. Quickprop and Rprop.

Algorithms↗
PubMed2005

Biological networks and analysis of experimental data in drug discovery.

Cellular life can be represented and studied as the 'interactome'--a dynamic network of biochemical reactions and signaling interactions between active proteins. Systemic networks analysis can be used for the integration and functional interpretation of high-throughput experimental data, which are abundant in drug discovery but currently poorly utilized. The composition and topology of complex networks are closely associated with vital cellular functions, which have important implications for life science research. Here we outline recent advances in the field, available tools and applications of network analysis in drug discovery.

Computer Simulation↗
PubMed1995

Development of a nursing diagnosis system using a back-propagation neural network model: an application for stomach cancer patients.

Neural networks have recently attracted considerable attention in the field of classification and in other areas. This paper discusses an experiment using a back-propagation neural network model applied to nursing diagnosis. The network's structure has three layers: 1) an input layer for representing signs and symptoms, 2) an output layer for nursing diagnosis, 3) a hidden layer. A first prototype of a nursing diagnosis system for stomach cancer patients was developed with 87 nodes for the input layer and 5 nodes for the output layer of 23 nursing diagnoses. It turned out that a model that learned 10,000 times as fast and had 5 nodes of hidden layers, a 0.5 momentum, and a 0.5 learning coefficient is the optimal one with a hitting ratio 0.76.

Computer Simulation↗
PubMed2004

Encoding nondeterministic fuzzy tree automata into recursive neural networks.

Fuzzy neural systems have been a subject of great interest in the last few years, due to their abilities to facilitate the exchange of information between symbolic and subsymbolic domains. However, the models in the literature are not able to deal with structured organization of information, that is typically required by symbolic processing. In many application domains, the patterns are not only structured, but a fuzziness degree is attached to each subsymbolic pattern primitive. The purpose of this paper is to show how recursive neural networks, properly conceived for dealing with structured information, can represent nondeterministic fuzzy frontier-to-root tree automata. Whereas available prior knowledge expressed in terms of fuzzy state transition rules are injected into a recursive network, unknown rules are supposed to be filled in by data-driven learning. We also prove the stability of the encoding algorithm, extending previous results on the injection of fuzzy finite-state dynamics in high-order recurrent networks.

Algorithms↗
PubMed2004

Preliminary studies on the in silico evolution of biochemical networks.

Due to the variety and importance of roles performed by signalling networks, understanding their function and evolution is of great interest. Signalling networks allow organisms to process and react to changes in their internal and external environment. Current estimates suggest that two to three percent of all genomes code for proteins involved in signalling networks. The study of signalling networks is hindered by the complexities of the networks and difficulties in ascribing function to form. For example, a very complex dense network might comprise eighty or more densely connected proteins. In the majority of cases there is very little understanding of how these networks process signals. Unlike in electronics, where there is a broad practical and theoretical understanding of how to construct devices that can process almost any kind of signal, in biological signalling networks there is no equivalent theory. Part of the problem stems from the fact that in most cases it is unknown what particular signal processing circuits would look like in a biological form. This paper describes the evolutionary methods used to generate networks with particular signal- and computational-processing capabilities. The techniques involved are described, and the approach is illustrated by evolving computational circuits such as multiplication, radicals and logarithmic functions. The experiments also illustrate the evolution of modularity within biochemical reaction networks.

Biochemistry↗
PubMed2006

Learning functional structure from fMR images.

We propose a novel method using Bayesian networks to learn the structure of effective connectivity among brain regions involved in a functional MR experiment. The approach is exploratory in the sense that it does not require an a priori model as in the earlier approaches, such as the Structural Equation Modeling or Dynamic Causal Modeling, which can only affirm or refute the connectivity of a previously known anatomical model or a hypothesized model. The conditional probabilities that render the interactions among brain regions in Bayesian networks represent the connectivity in the complete statistical sense. The present method is applicable even when the number of regions involved in the cognitive network is large or unknown. We demonstrate the present approach by using synthetic data and fMRI data collected in silent word reading and counting Stroop tasks.

Adult↗
PubMed2006

A neuronal network for the logic of Limax learning.

We construct a neuronal network to model the logic of associative conditioning as revealed in experimental results using the terrestrial mollusk Limax maximus. We show, in particular, how blocking to a previously conditioned stimulus in the presence of the unconditional stimulus, can emerge as a dynamical property of the network. We also propose experiments to test the new model.

Action Potentials↗
PubMed2004

Localized activity patterns in excitatory neuronal networks.

The existence of localized activity patterns, or bumps, has been investigated in a variety of spatially distributed neuronal network models that contain both excitatory and inhibitory coupling between cells. Here we show that a neuronal network with purely excitatory synaptic coupling can exhibit localized activity. Bump formation ensues from an initial transient synchrony of a localized group of cells, followed by the emergence of desynchronized activity within the group. Transient synchrony is shown to promote recruitment of cells into the bump, while desynchrony is shown to be good for curtailing recruitment and sustaining oscillations of those cells already within the bump. These arguments are based on the geometric structure of the phase space in which solutions of the model equations evolve. We explain why bump formation and bump size are very sensitive to initial conditions and changes in parameters in this type of purely excitatory network, and we examine how short-term synaptic depression influences the characteristics of bump formation.

Computer Simulation↗
PubMed2000

The number of synaptic inputs and the synchrony of large, sparse neuronal networks.

The prevalence of coherent oscillations in various frequency ranges in the central nervous system raises the question of the mechanisms that synchronize large populations of neurons. We study synchronization in models of large networks of spiking neurons with random sparse connectivity. Synchrony occurs only when the average number of synapses, M, that a cell receives is larger than a critical value, Mc. Below Mc, the system is in an asynchronous state. In the limit of weak coupling, assuming identical neurons, we reduce the model to a system of phase oscillators that are coupled via an effective interaction, gamma. In this framework, we develop an approximate theory for sparse networks of identical neurons to estimate Mc analytically from the Fourier coefficients of gamma. Our approach relies on the assumption that the dynamics of a neuron depend mainly on the number of cells that are presynaptic to it. We apply this theory to compute Mc for a model of inhibitory networks of integrate-and-fire (I&F) neurons as a function of the intrinsic neuronal properties (e.g., the refractory period Tr), the synaptic time constants, and the strength of the external stimulus, Iext. The number Mc is found to be nonmonotonous with the strength of Iext. For Tr = 0, we estimate the minimum value of Mc over all the parameters of the model to be 363.8. Above Mc, the neurons tend to fire in smeared one-cluster states at high firing rates and smeared two-or-more-cluster states at low firing rates. Refractoriness decreases Mc at intermediate and high firing rates. These results are compared to numerical simulations. We show numerically that systems with different sizes, N, behave in the same way provided the connectivity, M, is such that 1/Meff = 1/M - 1/N remains constant when N varies. This allows extrapolating the large N behavior of a network from numerical simulations of networks of relatively small sizes (N = 800 in our case). We find that our theory predicts with remarkable accuracy the value of Mc and the patterns of synchrony above Mc, provided the synaptic coupling is not too large. We also study the strong coupling regime of inhibitory sparse networks. All of our simulations demonstrate that increasing the coupling strength reduces the level of synchrony of the neuronal activity. Above a critical coupling strength, the network activity is asynchronous. We point out a fundamental limitation for the mechanisms of synchrony relying on inhibition alone, if heterogeneities in the intrinsic properties of the neurons and spatial fluctuations in the external input are also taken into account.

Algorithms↗
PubMed2003

Artificial neural network analysis of malaria severity through aggregation and deformability parameters of erythrocytes.

The erythrocyte aggregation and deformability of blood samples obtained from normal subjects and malaria patients are determined by microscopic imaging and laser aggregometry techniques, and optical hemorheometer, respectively. By these techniques several parameters are determined but four parameters, aggregate sedimentation velocity (ASV), effective number of cells (ENC), process completion time (PCT) and mean filtration time (MFT), show significant variation in malaria patients compared to that of healthy subjects. For malaria severity analysis artificial neural network (ANN), based on feedforward-error back-propagation algorithm in a supervisory training mode is proposed. This network is first trained for different number of epochs ranging from 20 to 50 by set of patterns and at 30 epochs training session the minimum mean square error (MSE) between desired and actual output is obtained. By applying the same procedure the test patterns belonging to normal, non-severe, severe, and highly severe malaria (NSM, SM and HSM) are identified. The results show that malaria with high severity is classified accurately (100%). The success of classification for non-severe and mildly-severe malaria ranges from 60% to 80%.

Equipment Design↗
PubMedDate not supplied

An efficient learning algorithm for improving generalization performance of radial basis function neural networks.

This paper presents an efficient recursive learning algorithm for improving generalization performance of radial basis function (RBF) neural networks. The approach combines the rival penalized competitive learning (PRCL) [Xu, L., Kizyzak, A. & Oja, E. (1993). Rival penalized competitive learning for clustering analysis, RBF net and curve detection, IEEE Transactions on Neural Networks, 4, 636-649] and the regularized least squares (RLS) to provide an efficient and powerful procedure for constructing a minimal RBF network that generalizes very well. The RPCL selects the number of hidden units of network and adjusts centers, while the RLS constructs the parsimonious network and estimates the connection weights. In the RLS we derived a simple recursive algorithm, which needs no matrix calculation, and so largely reduces the computational cost. This combined algorithm significantly enhances the generalization performance and the real-time capability of the RBF networks. Simulation results of three different problems demonstrate much better generalization performance of the present algorithm over other existing similar algorithms.

Algorithms↗
PubMed2004

Simulated apoptosis/neurogenesis regulates learning and memory capabilities of adaptive neural networks.

Characterization of neuronal death and neurogenesis in the adult brain of birds, humans, and other mammals raises the possibility that neuronal turnover represents a special form of neuroplasticity associated with stress responses, cognition, and the pathophysiology and treatment of psychiatric disorders. Multilayer neural network models capable of learning alphabetic character representations via incremental synaptic connection strength changes were used to assess additional learning and memory effects incurred by simulation of coordinated apoptotic and neurogenic events in the middle layer. Using a consistent incremental learning capability across all neurons and experimental conditions, increasing the number of middle layer neurons undergoing turnover increased network learning capacity for new information, and increased forgetting of old information. Simulations also showed that specific patterns of neural turnover based on individual neuronal connection characteristics, or the temporal-spatial pattern of neurons chosen for turnover during new learning impacts new learning performance. These simulations predict that apoptotic and neurogenic events could act together to produce specific learning and memory effects beyond those provided by ongoing mechanisms of connection plasticity in neuronal populations. Regulation of rates as well as patterns of neuronal turnover may serve an important function in tuning the informatic properties of plastic networks according to novel informational demands. Analogous regulation in the hippocampus may provide for adaptive cognitive and emotional responses to novel and stressful contexts, or operate suboptimally as a basis for psychiatric disorders. The implications of these elementary simulations for future biological and neural modeling research on apoptosis and neurogenesis are discussed.

Animals↗
PubMedDate not supplied

Constructing a query-able radial basis function artificial neural network.

Artificial neural networks will be more widely accepted as standard engineering tools if their reasoning process can be made less opaque. This paper describes NetQuery, an explanation mechanism that extracts meaningful explanations from trained Radial Basis Function (RBF) networks. RBF networks are well suited for explanation generation because they contain a set of locally tuned units. Standard RBF networks are modified to identify dependencies between the inputs, to be sparsely connected, and to have an easily interpretable output layer. Given these modifications, the network architecture can be used to extract "Why?" and "Why not?" explanations from the network in terms of excitatory and inhibitory in-puts and their linear relationships, greatly simplified by a run-time pruning algorithm. These query results are validated by creating an expert system based on the explanations. NetQuery is also able to inform a user about a possible change in category for a given pattern by responding to a "How can I...?" query. This kind of query is extremely useful when analyzing the quality of a pattern set.

Algorithms↗
PubMed2005

Using adaline neural network for performance improvement of smart antennas in TDD wireless communications.

In time-division-duplex (TDD) mode wireless communications, downlink beamforming performance of a smart antenna system at the base station can be degraded due to variation of spatial signature vectors corresponding to mobile users especially in fast fading scenarios. To mitigate this, downlink beams must be controlled by properly adjusting their weight vectors in response to changing propagation dynamics. This can be achieved by modeling the spatial signature vectors in the uplink period and then predicting them to be used as beamforming weight vectors for the new mobile position in the downlink transmission period. We show that ADAptive LInear NEuron (ADALINE) network modeling based prediction of spatial signatures provides certain level of performance improvement compared to conventional beamforming method that employs spatial signature obtained in previous uplink interval. We compare the performance of ADALINE with autoregressive (AR) modeling based predictions under varying channel propagation (mobile speed, multipath angle spread, and number of multipaths), and filter order/delay conditions. ADALINE modeling outperforms AR modeling in terms of downlink SNR improvement and relative error improvement especially under high mobile speeds, i.e., V = 100 km/h.

Algorithms↗
PubMed2006

A neural network-based novelty detector for image sequence analysis.

This paper proposes a new model of "novelty detection" for image sequence analysis using neural networks. This model uses the concept of artificially generated negative data to form closed decision boundaries using a multilayer perceptron. The neural network output is novelty filtered by thresholding the output of multiple networks (one per known class) to which the sample is input and clustered for determining which clusters represent novel classes. After labeling these novel clusters, new networks are trained on this data. We perform experiments with video-based image sequence data containing a number of novel classes. The performance of the novelty filter is evaluated using two performance metrics and we compare our proposed model on the basis of these with five baseline novelty detectors. We also discuss the results of retraining each model after novelty detection. On the basis of Chi-square performance metric, we prove at 5 percent significance level that our optimized novelty detector performs at the same level as an ideal novelty detector that does not make any mistakes.

Algorithms↗