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 1,297 records · Page 72Linked to original sources

PubMed2004

Integrative technology for the twenty-first century.

Presented is the concept of Integrative Technology, the intersection of the precision assembly of matter (nanotechnology), coupled with the functional building blocks of nature (biotechnology), and fused by the network flow of spatiotemporal information (informatics). The power of Integrative Technology is illuminated through an illustrative example; the engineering of nano-sized excitable vesicles with the ability to intrinsically process information. The fusion of the tools of nanotechnology and biotechnology to produce excitable vesicles is described, as is the mechanics of information flow that ultimately lead to the manifestations of emergent higher-order behavior. Finally, the potential of using systems engineered and produced from nanoscale components to create complex systems and materials that manifest embedded functional behavior is discussed.

Biomimetics↗

PubMed2001

Improvement of generalization ability for identifying dynamical systems by using universal learning networks.

This paper studies how the generalization ability of models of dynamical systems can be improved by taking advantage of the second order derivatives of the outputs with respect to the external inputs. The proposed method can be regarded as a direct implementation of the well-known regularization technique using the higher order derivatives of the Universal Learning Networks (ULNs). ULNs consist of a number of interconnected nodes where the nodes may have any continuously differentiable nonlinear functions in them and each pair of nodes can be connected by multiple branches with arbitrary time delays. A generalized learning algorithm has been derived for the ULNs, in which both the first order derivatives (gradients) and the higher order derivatives are incorporated. First, the method for computing the second order derivatives of ULNs is discussed. Then, a new method for implementing the regularization term is presented. Finally, simulation studies on identification of a nonlinear dynamical system with noises are carried out to demonstrate the effectiveness of the proposed method. Simulation results show that the proposed method can improve the generalization ability of neural networks significantly, especially in terms that (1) the robust network can be obtained even when the branches of trained ULNs are destructed, and (2) the obtained performance does not depend on the initial parameter values.

Computer Simulation↗

PubMed2004

Neocognitron capable of incremental learning.

This paper proposes a new neocognitron that accepts incremental learning, without giving a severe damage to old memories or reducing learning speed. The new neocognitron uses a competitive learning, and the learning of all stages of the hierarchical network progresses simultaneously. To increase the learning speed, conventional neocognitrons of recent versions sacrificed the ability of incremental learning, and used a technique of sequential construction of layers, by which the learning of a layer started after the learning of the preceding layers had completely finished. If the learning speed is simply set high for the conventional neocognitron, simultaneous construction of layers produces many garbage cells, which become always silent after having finished the learning. The proposed neocognitron with a new learning method can prevent the generation of such garbage cells even with a high learning speed, allowing incremental learning.

Cognition↗

PubMed2000

Implementation of a pulse coupled neural network in FPGA.

The Pulse Coupled neural network, PCNN, is a biologically inspired neural net and it can be used in various image analysis applications, e.g. time-critical applications in the field of image pre-processing like segmentation, filtering, etc. a VHDL implementation of the PCNN targeting FPGA was undertaken and the results presented here. The implementation contains many interesting features. By pipelining the PCNN structure a very high throughput of 55 million neuron iterations per second could be achieved. By making the coefficients re-configurable during operation, a complete recognition system could be implemented on one, or maybe two, chip(s). Reconsidering the ranges and resolutions of the constants may save a lot of hardware, since the higher resolution requires larger multipliers, adders, memories etc.

Analog-Digital Conversion↗

PubMed1996

A knowledge-based model construction approach to medical decision making.

We present a framework for representing the probabilistic effects of actions and contingent treatment plans. Our language has a well-defined declarative semantics and we have developed an implemented algorithm (named BNG) that generates Bayesian networks (BN) to compute the posterior probabilities of queries. In this paper we address the problem of projecting a contingent treatment plan by automatically constructing a structure of interrelated BNs, which we call a BN-graph, and applying the available propagation procedures on it. To address the optimal plan generation, we base our approach on the observation that normally the target plan space has a well-defined structure. We provide a language to describe plan spaces which resembles a programming language with loops and conditionals. We briefly present the procedures for finding the optimal plan(s) from such specified plan spaces.

Acute Disease↗

PubMed1995

Self-organizing maps and molecular similarity.

Self-organizing maps generated by Kohonen neural networks provide a method for transforming multidimensional problems into lower dimensional problems. Here, a Kohonen network is used to generate two-dimensional representations of the electrostatic potential about the ring structures of histamine H2 agonists. Previous work by J. Gasteiger and X. Li (Angew. Chem. Int. Ed. Engl. 1994, 33, 643) has shown the usefulness of such a method for classifying molecules as muscarinic or nicotinic agonists. Here, the method is extended to rank histamine H2 agonists in order of biological activity.

Computer Graphics↗

PubMed1995

Clinical applications of Bayesian belief networks in pathology.

Bayesian belief networks (BBNs) are a novel tool for representing knowledge about diagnostic decision making and for obtaining a numerical measure of certainty in the final diagnosis. Belief networks have been applied to the pathological assessment of breast, prostate and skin lesions and have been shown to provide consistency in the grading of microscopic features and improve diagnosis. These applications are reviewed in the current paper. The application of BBNs has been further facilitated through the use of standardised imagery which is stored digitally and used to enter evidence into a BBN. It is predicted that the further development of BBNs with improved logical capabilities represent the key to improved decision making in pathology.

Bayes Theorem↗

PubMed2004

Are multi-layer backpropagation networks catastrophically amnesic?

Connectionist models with a backpropagation learning rule are known to have a serious problem. Such models exhibit catastrophic interference (or forgetting) with sequential training. Having learned a set of patterns, if the model is trained on another set of patterns, its performance on the first set can dramatically deteriorate very rapidly. The present study reconsiders this issue with four simulations. The model learned arithmetic facts sequentially, but the interference was only modest with random (hence approximately orthogonal) inputs. Essentially the same result was obtained when the inputs are made less orthogonal by adding irrelevant elements. Reducing the number of hidden units did not have major effects. This study suggests that the interference problem has been somewhat overstated.

Algorithms↗

PubMed1997

Construction of a Bayesian network for mammographic diagnosis of breast cancer.

Bayesian networks use the techniques of probability theory to reason under uncertainty, and have become an important formalism for medical decision support systems. We describe the development and validation of a Bayesian network (MammoNet) to assist in mammographic diagnosis of breast cancer. MammoNet integrates five patient-history features, two physical findings, and 15 mammographic features extracted by experienced radiologists to determine the probability of malignancy. We outline the methods and issues in the system's design, implementation, and evaluation. Bayesian networks provide a potentially useful tool for mammographic decision support.

Bayes Theorem↗

PubMed2006

Stable concurrent synchronization in dynamic system networks.

In a network of dynamical systems, concurrent synchronization is a regime where multiple groups of fully synchronized elements coexist. In the brain, concurrent synchronization may occur at several scales, with multiple "rhythms" interacting and functional assemblies combining neural oscillators of many different types. Mathematically, stable concurrent synchronization corresponds to convergence to a flow-invariant linear subspace of the global state space. We derive a general condition for such convergence to occur globally and exponentially. We also show that, under mild conditions, global convergence to a concurrently synchronized regime is preserved under basic system combinations such as negative feedback or hierarchies, so that stable concurrently synchronized aggregates of arbitrary size can be constructed. Robustnesss of stable concurrent synchronization to variations in individual dynamics is also quantified. Simple applications of these results to classical questions in systems neuroscience and robotics are discussed.

Animals↗

PubMed2000

Blind signal processing by the adaptive activation function neurons.

The aim of this paper is to study an Information Theory based learning theory for neural units endowed with adaptive activation functions. The learning theory has the target to force the neuron to approximate the input-output transference that makes it flat (uniform) the probability density function of its output or, equivalently, that maximizes the entropy of the neuron response. Then, a network of adaptive activation function neurons is studied, and the effectiveness of the new structure is tested on Independent Component Analysis (ICA) problems. The new ICA neural algorithm is compared with the closely related 'Mixture of Densities' (MOD) technique by Xu et al.. Both simulation results and structural comparison show the new method is effective and more efficient in computational complexity.

Algorithms↗

PubMed2005

The efficiency of multi-target drugs: the network approach might help drug design.

Despite considerable progress in genome- and proteome-based high-throughput screening methods and rational drug design, the number of successful single-target drugs did not increase appreciably during the past decade. Network models suggest that partial inhibition of a surprisingly small number of targets can be more efficient than the complete inhibition of a single target. This and the success stories of multi-target drugs and combinatorial therapies led us to suggest that systematic drug-design strategies should be directed against multiple targets. We propose that the final effect of partial, but multiple, drug actions might often surpass that of complete drug action at a single target. The future success of this novel drug-design paradigm will depend not only on a new generation of computer models to identify the correct multiple targets and their multi-fitting, low-affinity drug candidates but also on more-efficient in vivo testing.

Computational Biology↗

PubMed2006

Associative memory design for 256 gray-level images using a multilayer neural network.

A design procedure is presented for neural associative memories storing gray-scale images. It is an evolution of a previous work based on the decomposition of the image with 2L gray levels into L binary patterns, stored in L uncoupled neural networks. In this letter, an L-layer neural network is proposed with both intralayer and interlayer connections. The connections between different layers introduce interactions among all the neurons, increasing the recall performance with respect to the uncoupled case. In particular, the proposed network can store images with the commonly used number of 256 gray levels instead of 16, as in the previous approach.

Algorithms↗

PubMed2003

Hybrid integrate-and-fire model of a bursting neuron.

We present a reduction of a Hodgkin-Huxley (HH)--style bursting model to a hybridized integrate-and-fire (IF) formalism based on a thorough bifurcation analysis of the neuron's dynamics. The model incorporates HH--style equations to evolve the subthreshold currents and includes IF mechanisms to characterize spike events and mediate interactions between the subthreshold and spiking currents. The hybrid IF model successfully reproduces the dynamic behavior and temporal characteristics of the full model over a wide range of activity, including bursting and tonic firing. Comparisons of timed computer simulations of the reduced model and the original model for both single neurons and moderately sized networks (n < or = 500) show that this model offers improvement in computational speed over the HH--style bursting model.

Action Potentials↗

PubMed2005

An artificial neural network for predicting the incidence of radiation pneumonitis.

A method to predict radiation-induced pneumonitis (RP) using an artificial neural network (ANN) was investigated. A retrospective study was applied to the clinical data from 142 patients who have been treated with three-dimensional conformal radiotherapy for tumors in the thoracic region. These data were classified, based on their treatment outcome, into two patient clusters: with RP (Np=26) and without RP (Np= 116). An ANN was designed as a classifier. To perform the classification, a patient-treatment outcome with RP was assigned a value of 1, and a patient treatment outcome without RP was assigned a value of -1. The input of the ANN was limited to the patient lung dose-volume data only. A volume vector (VD) that describes patient lung subvolumes receiving more than a set of threshold doses was used as the network input variable. A zero value was used as the threshold to set the output value into -1 or 1. Three ANNs (ANN_1, ANN_2, and ANN_3), each with three layers, were trained to perform this classification function and to show the effect of training data on the ANN performance. Radial basis function was applied as the hidden layer neuron activation function and a sigmoid function was selected as the output layer neuron function. Backpropagation with a conjugate gradient algorithm was used to train the network. ANN_1 was trained and tested by using the leave-one-out method. ANN_2 was trained by randomly selecting 2/3 of the patient data, and tested by the remaining 1/3 of the data. ANN_3 was trained by a user selecting 2/3 of the patient data, and tested by the remaining 1/3 of the data. The predictive accuracy was verified as the area under a receiver operator characteristic (ROC) curve. The correct classification rates of 73% for RP cases, and 99% for non-RP cases were obtained from ANN_1. The corresponding correct classification rates of 44% for RP cases, and 89% for non-RP cases were obtained from ANN_2. From the ANN_3 test phase, the corresponding correct classification rates of 55% for RP cases, and 95% non-RP cases were achieved. The area under ROC curve was 0.85+/-0.05, 0.68+/-0.10, and 0.81+/-0.09 for ANN_1, ANN _2, and ANN_3, respectively, within its asymmetric 95% confidence interval. The sensitivity was 95%, 57%, and 71%, and the specificity was 94%, 88%, and 90% for ANN_1, ANN_2, and ANN_3, respectively. Preliminary results suggest that the ANN approach provides a useful tool for the prediction of radiation-induced lung pneumonitis, using the patient lung dose-volume information.

Algorithms↗

PubMed2001

[Input layer self-construction neural network and its use in multivariant calibration of infrared spectra].

In order to solve the problems of feature extraction and calibration modelling in the area of quantitatively infrared spectra analysis, an input layer self-constructive neural network (ILSC-NN) is proposed. Before the NN training process, the training data is firstly analyzed and some prior knowledge about the problem is obtained. During the training process, the number of the input neurons is determined adaptively based on the prior knowledge. Meantime, the network parameters are also determined. This algorithm of the NN model helps to increase the efficiency of calibration modelling. The test experiment of quantitative analysis using simulated spectral data showed that this modelling method could not only achieve efficient wavelength selection, but also remarkably reduce the random and non-linear noises.

Algorithms↗

PubMed2002

Neural networks in cardiac electrophysiological signal classification.

The aim of this work was to develop a method by which intra-cardiac electrograms could be classified. A new algorithm for training this particular network has been established and applied to the task of finding the onset times of intra-cardiac electrograms. The algorithm is based on adding a choice function to the combination function of each neuron. The choice function enables the network to consider delays in each of its synapses. The gradient of error is then calculated with respect to the weights and delays. A synaptic delay-based artificial neural network was implemented using MATLAB and used to detect the onset times of the atrial, His and ventricular electrograms from the His catheter recordings. Results from a subset of a clinical, 12-channel electrophysiology study demonstrated the ability of the network to successfully identify peak potentials and onset times. Errors in detection of onset times were in the range of 1-2 ms. This method, which does not utilise traditional windowing and/or thresholding operations, can be effectively used to detect temporal patterns in a range of electrophysiological and biological signals.

Algorithms↗

PubMed2007

Exact subthreshold integration with continuous spike times in discrete-time neural network simulations.

Very large networks of spiking neurons can be simulated efficiently in parallel under the constraint that spike times are bound to an equidistant time grid. Within this scheme, the subthreshold dynamics of a wide class of integrate-and-fire-type neuron models can be integrated exactly from one grid point to the next. However, the loss in accuracy caused by restricting spike times to the grid can have undesirable consequences, which has led to interest in interpolating spike times between the grid points to retrieve an adequate representation of network dynamics. We demonstrate that the exact integration scheme can be combined naturally with off-grid spike events found by interpolation. We show that by exploiting the existence of a minimal synaptic propagation delay, the need for a central event queue is removed, so that the precision of event-driven simulation on the level of single neurons is combined with the efficiency of time-driven global scheduling. Further, for neuron models with linear subthreshold dynamics, even local event queuing can be avoided, resulting in much greater efficiency on the single-neuron level. These ideas are exemplified by two implementations of a widely used neuron model. We present a measure for the efficiency of network simulations in terms of their integration error and show that for a wide range of input spike rates, the novel techniques we present are both more accurate and faster than standard techniques.

Action Potentials↗