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 937 records · Page 52Linked to original sources
PubMed2006

Adaptive filtering with the self-organizing map: a performance comparison.

In this paper we provide an in-depth evaluation of the SOM as a feasible tool for nonlinear adaptive filtering. A comprehensive survey of existing SOM-based and related architectures for learning input-output mappings is carried out and the application of these architectures to nonlinear adaptive filtering is formulated. Then, we introduce two simple procedures for building RBF-based nonlinear filters using the Vector-Quantized Temporal Associative Memory (VQTAM), a recently proposed method for learning dynamical input-output mappings using the SOM. The aforementioned SOM-based adaptive filters are compared with standard FIR/LMS and FIR/LMS-Newton linear transversal filters, as well as with powerful MLP-based filters in nonlinear channel equalization and inverse modeling tasks. The obtained results in both tasks indicate that SOM-based filters can consistently outperform powerful MLP-based ones.

Algorithms↗
PubMed2006

Advanced visualization of self-organizing maps with vector fields.

Self-Organizing Maps have been applied in various industrial applications and have proven to be a valuable data mining tool. In order to fully benefit from their potential, advanced visualization techniques assist the user in analyzing and interpreting the maps. We propose two new methods for depicting the SOM based on vector fields, namely the Gradient Field and Borderline visualization techniques, to show the clustering structure at various levels of detail. We explain how this method can be used on aggregated parts of the SOM that show which factors contribute to the clustering structure, and show how to use it for finding correlations and dependencies in the underlying data. We provide examples on several artificial and real-world data sets to point out the strengths of our technique, specifically as a means to combine different types of visualizations offering effective multidimensional information visualization of SOMs.

Algorithms↗
PubMed2006

Large-scale neural models and dynamic causal modelling.

Dynamic causal modelling (DCM) is a method for estimating and making inferences about the coupling among small numbers of brain areas, and the influence of experimental manipulations on that coupling [Friston, K.J., Harrison, L., Penny, W., 2003 Dynamic causal modelling. Neuroimage 19, 1273-1302]. Large-scale neural modelling aims to construct neurobiologically grounded computational models with emergent behaviours that inform our understanding of neuronal systems. One such model has been used to simulate region-specific BOLD time-series [Horwitz, B., Friston, K.J., Taylor, J.G., 2000. Neural modeling and functional brain imaging: an overview. Neural Netw. 13, 829-846]. DCM was used to make inferences about effective connectivity using data generated by a model implementing a visual delayed match-to-sample task [Tagamets, M.A., Horwitz, B., 1998. Integrating electrophysiological and anatomical experimental data to create a large-scale model that simulates a delayed match-to-sample human brain imaging study. Cereb. Cortex 8, 310-320]. The aim was to explore the validity of inferences made using DCM about the connectivity structure and task-dependent modulatory effects, in a system with a known connectivity structure. We also examined the effects of misspecifying regions of interest. Models with hierarchical connectivity and reciprocal connections were examined using DCM and Bayesian Model Comparison [Penny, W.D., Stephan, K.E., Mechelli, A., Friston, K.J., 2004. Comparing dynamic causal models. Neuroimage 22, 1157-1172]. This approach revealed strong evidence for those models with correctly specified anatomical connectivity. Furthermore, Bayesian model comparison favoured those models when bilinear effects corresponded to their implementation in the neural model. These findings generalised to an extended model with two additional areas and reentrant circuits. The conditional uncertainty of coupling parameter estimates increased in proportion to the number of incorrectly specified regions. These results highlight the role of neural models in establishing the validity of estimation and inference schemes. Specifically, Bayesian model comparison confirms the validity of DCM in relation to a well-characterised and comprehensive neuronal model.

Bayes Theorem↗
PubMed2005

Grounding words in perception and action: computational insights.

We use words to communicate about things and kinds of things, their properties, relations and actions. Researchers are now creating robotic and simulated systems that ground language in machine perception and action, mirroring human abilities. A new kind of computational model is emerging from this work that bridges the symbolic realm of language with the physical realm of real-world referents. It explains aspects of context-dependent shifts of word meaning that cannot easily be explained by purely symbolic models. An exciting implication for cognitive modeling is the use of grounded systems to 'step into the shoes' of humans by directly processing first-person-perspective sensory data, providing a new methodology for testing various hypotheses of situated communication and learning.

Cognition↗
PubMed2003

Bayesian models of object perception.

The human visual system is the most complex pattern recognition device known. In ways that are yet to be fully understood, the visual cortex arrives at a simple and unambiguous interpretation of data from the retinal image that is useful for the decisions and actions of everyday life. Recent advances in Bayesian models of computer vision and in the measurement and modeling of natural image statistics are providing the tools to test and constrain theories of human object perception. In turn, these theories are having an impact on the interpretation of cortical function.

Animals↗
PubMedDate not supplied

Bionics, biological systems and the principle of optimal design.

The living world is an exciting and inexhaustible source of high performance solutions to the multitude of biological problems, which were attained as a result of a natural selection, during the millions and millions years evolution of life on Earth. This work presents and comments some examples of high performances of living beings, in the light of the universal principle governing the realm of living matter: Optimal Design Principle. At the same time, the transfer of these optimal solutions, from living matter to the technologies, is also discussed. This transfer is offering new and fertile perspectives to future technologies, which must be more efficient, cheaper and in perfect harmony with the biosphere.

Animals↗
PubMed2003

Self-programming machines (II): Network of self-programming machines driving an Ashby homeostat.

The progress in artificial intelligence enables us to conceive adaptive systems whose characteristics are nearer and nearer to those of living beings. These characteristics though depend on ingenious choices by the designer of these systems: Initial conditions, parameters, optimisation functions, gradient and measure of fitness within the environment. Nevertheless, in living systems which are non-finalist, there are no programmers or designers to conceive of such ingenious choices. Our paper "Self-Programming Machines (I)" presents a non-finalist model since initial states and functions are randomly chosen at the beginning and once and for all. In spite of the fact that they are non-finalist, these machines always stabilise at fixed points when they are connected to an external process. This paper studies the dynamics of a mono-layered network of self-programming machines driving a real device. "the Ashby homeostat", and shows the striking properties of such networks. This system stabilises only at fixed points even if it is subjected to small perturbations or intentional breakdowns such as a reversal of power supply or disconnection of one or several motors. Real and simulated experiences are compared and theoretical results are demonstrated.

Artificial Intelligence↗
PubMed2004

Properties of the Hubert-Arabie adjusted Rand index.

This article provides an investigation of cluster validation indices that relates 4 of the indices to the L. Hubert and P. Arabie (1985) adjusted Rand index--the cluster validation measure of choice (G. W. Milligan & M. C. Cooper, 1986). It is shown how these other indices can be "roughly" transformed into the same scale as the adjusted Rand index. Furthermore, in-depth explanations are given of why classification rates should not be used in cluster validation research. The article concludes by summarizing several properties of the adjusted Rand index across many conditions and provides a method for testing the significance of observed adjusted Rand indices.

Artificial Intelligence↗
PubMed2002

Model for a robust neural integrator.

Integrator circuits in the brain show persistent firing that reflects the sum of previous excitatory and inhibitory inputs from external sources. Integrator circuits have been implicated in parametric working memory, decision making and motor control. Previous work has shown that stable integrator function can be achieved by an excitatory recurrent neural circuit, provided synaptic strengths are tuned with extreme precision (better than 1% accuracy). Here we show that integrator circuits can function without fine tuning if the neuronal units have bistable properties. Two specific mechanisms of bistability are analyzed, one based on local recurrent excitation, and the other on the voltage-dependence of the NMDA (N-methyl-D-aspartate) channel. Neither circuit requires fine tuning to perform robust integration, and the latter actually exploits the variability of neuronal conductances.

Computer Simulation↗
PubMed1999

A confident decision support system for interpreting electrocardiograms.

Computer-aided interpretation of electrocardiograms (ECGs) is widespread but many physicians hesitate to rely on the computer, because the advice is presented without information about the confidence of the advice. The purpose of this work was to develop a method to validate the advice of a computer by estimating the error of an artificial neural network output. A total of 1249 ECGs, recorded with computerized electrocardiographs, on patients who had undergone diagnostic cardiac catheterization were studied. The material consisted of two groups, 414 patients with and 835 without anterior myocardial infarction. The material was randomly divided into three data sets. The first set was used to train an artificial neural network for the diagnosis of anterior infarction. The second data set was used to calculate the error of the network outputs. The last data set was used to test the network performance and to estimate the error of the network outputs. The performance of the neural network, measured as the area under the receiver operating characteristic (ROC) curve, was 0.887 (0.845-0.922). The 25% test ECGs with the lowest error estimates had an area under the ROC curve as high as 0.995 (0.982-1.000), i.e. almost all of these ECGs were correctly classified. Neural networks can therefore be trained to diagnose myocardial infarction and to signal when the advice is given with great confidence or when it should be considered more carefully. This method increases the possibility that artificial neural networks will be accepted as reliable decision support systems in clinical practice.

Bayes Theorem↗
PubMed2004

Determining the receptive field of a neural filter.

In this paper, a method for determining the receptive field and the structure of hidden layers of a neural filter (NF) was developed and evaluated. With the proposed method, redundant units are removed from input and hidden layers in an NF based on the influence of removal of units on the error between output and teaching images. By performing the removal of units and retraining for recovery of the loss of the removal repeatedly, the receptive field and a reduced structure of hidden layers are determined. Experiments with NFs were performed for acquiring the function of a known filter, for the reduction of noise in natural images and for the reduction of noise in medical image sequences. By use of the proposed method, redundant units were able to be removed from NFs, while the performance of the NFs was maintained. Experimental results suggested that, with the proposed method, a reasonable receptive field for a given image-processing task could be determined, i.e., the receptive field of the NF trained to obtain the function of a filter corresponded to the kernel of the filter, and the receptive fields of the NFs for noise reduction gathered around the object pixels in the input regions of the NFs.

Algorithms↗
PubMed2004

A computational model for the development of multiple maps in primary visual cortex.

Primary visual cortex contains multiple maps of features of the visual scene, including visual field position, orientation, direction, ocular dominance and spatial frequency. The complex relationships between these maps provide clues to the strategies the cortex uses for representing and processing information. Here we simulate the combined development of all these map systems using a computational model, the elastic net. We show that this model robustly produces combined maps of these four variables that bear a close resemblance to experimental maps. In addition we show that the experimentally observed effects of monocular deprivation and single-orientation rearing can be reproduced in this model, and we make some testable predictions. These results provide strong support for the hypothesis that cortical representations attempt to optimize a trade-off between coverage and continuity.

Brain Mapping↗
PubMed1997

Model-based interpretation of complex and variable images.

The ultimate goal of machine vision is image understanding-the ability not only to recover image structure but also to know what it represents. By definition, this involves the use of models which describe and label the expected structure of the world. Over the past decade, model-based vision has been applied successfully to images of man-made objects. It has proved much more difficult to develop model-based approaches to the interpretation of images of complex and variable structures such as faces or the internal organs of the human body (as visualized in medical images). In such cases it has been problematic even to recover image structure reliably, without a model to organize the often noisy and incomplete image evidence. The key problem is that of variability. To be useful, a model needs to be specific-that is, to be capable of representing only 'legal' examples of the modelled object(s). It has proved difficult to achieve this whilst allowing for natural variability. Recent developments have overcome this problem; it has been shown that specific patterns of variability in shape and grey-level appearance can be captured by statistical models that can be used directly in image interpretation. The details of the approach are outlined and practical examples from medical image interpretation and face recognition are used to illustrate how previously intractable problems can now be tackled successfully. It is also interesting to ask whether these results provide any possible insights into natural vision; for example, we show that the apparent changes in shape which result from viewing three-dimensional objects from different viewpoints can be modelled quite well in two dimensions; this may lend some support to the 'characteristic views' model of natural vision.

Form Perception↗
PubMed2002

Storage capacity of attractor neural networks with depressing synapses.

We compute the capacity of a binary neural network with dynamic depressing synapses to store and retrieve an infinite number of patterns. We use a biologically motivated model of synaptic depression and a standard mean-field approach. We find that at T=0 the critical storage capacity decreases with the degree of the depression. We confirm the validity of our main mean-field results with numerical simulations.

Journal Article↗