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 973 records · Page 54Linked to original sources
PubMedDate not supplied

Image processing, diagnostic information extraction and quantitative assessment in pathology.

As we enter the information age we hold strong beliefs in the benefits of digital technology applied to pathology: numerical representation offers objectivity. Digital knowledge may indeed lead to significant information discovery, and, processing systems might be designed to allow a true evolution of capabilities. Questions arise whether the methodology underlying quantitative analysis provides the information that we need and whether it is appropriate for some of the problems encountered in diagnostic and prognostic histopathology. While one certainly would not dispute the value of statistical procedures, the clinical needs call for individual patient targeted prognosis.

Diagnostic Imaging↗
PubMed2000

A programmable VLSI filter architecture for application in real-time vision processing systems.

An architecture is proposed for the realization of real-time edge-extraction filtering operation in an Address-Event-Representation (AER) vision system. Furthermore, the approach is valid for any 2D filtering operation as long as the convolutional kernel F(p,q) is decomposable into an x-axis and a y-axis component, i.e. F(p,q)=H(p)V(q), for some rotated coordinate system [p,q]. If it is possible to find a coordinate system [p,q], rotated with respect to the absolute coordinate system a certain angle, for which the above decomposition is possible, then the proposed architecture is able to perform the filtering operation for any angle we would like the kernel to be rotated. This is achieved by taking advantage of the AER and manipulating the addresses in real time. The proposed architecture, however, requires one approximation: the product operation between the horizontal component H(p) and vertical component V(q) should be able to be approximated by a signed minimum operation without significant performance degradation. It is shown that for edge-extraction applications this filter does not produce performance degradation. The proposed architecture is intended to be used in a complete vision system known as the Boundary-Contour-System and Feature-Contour-System Vision Model, proposed by Grossberg and collaborators. The present paper proposes the architecture, provides a circuit implementation using MOS transistors operated in weak inversion, and shows behavioral simulation results at the system level operation and electrical simulation and experimental results at the circuit level operation of some critical subcircuits.

Computer Simulation↗
PubMed2000

Local linear independent component analysis based on clustering.

In standard Independent Component Analysis (ICA), a linear data model is used for a global description of the data. Even though linear ICA yields meaningful results in many cases, it can provide a crude approximation only for general nonlinear data distributions. In this paper a new structure is proposed, where local ICA models are used in connection with a suitable grouping algorithm clustering the data. The clustering part is responsible for an overall coarse nonlinear representation of the data, while linear ICA models of each cluster are used for describing local features of the data. The goal is to represent the data better than in linear ICA while avoiding computational difficulties related with nonlinear ICA. Several data grouping methods are considered, including standard K-means clustering, self-organizing maps, and neural gas. Connections to existing methods are discussed, and experimental results are given for artificial data and natural images. Furthermore, a general theoretical framework encompassing a large number of methods for representing data is introduced. These range from global, dense representation methods to local, very sparse coding methods. The proposed local ICA methods lie between these two extremes.

Algorithms↗
PubMed2002

Neuronal dynamics under periodic stimuli.

The convergence characteristics of a single dissipative Hopfield-type neuron with self-interaction under periodic external stimuli are considered. Sufficient conditions are established for associative encoding and recall of the periodic patterns associated with the external stimuli. Both continuous-time-continuous-state and discrete-time-continuous-state models are discussed. It is shown that when the neuronal gain is dominated by the neuronal dissipation on average, associative recall of the encoded temporal pattern is guaranteed and this is achieved by the global asymptotic stability of the encoded pattern.

Algorithms↗
PubMed2004

A self-stabilizing learning rule for minor component analysis.

The paper reviews single-neuron learning rules for minor component analysis and suggests a novel minor component learning rule. In this rule, the weight vector length is self-stabilizing, i.e., moving towards unit length in each learning step. In simulations with low- and medium-dimensional data, the performance of the novel learning rule is compared with previously suggested rules.

Algorithms↗
PubMed1996

A unified neural bigradient algorithm for robust PCA and MCA.

A new instantaneous-gradient search algorithm for computing a principal component or minor component type solution is proposed. The algorithm can use normalized Hebbian or anti-Hebbian learning in a unified formula. Starting from one-unit rule, a multi-unit algorithm is developed which can simultaneously extract several robust counterparts of the principal or minor eigenvectors of the data covariance matrix. Standard principal or minor components emerge as special cases from the general non-quadratic criterion. The learning rule is analyzed mathematically, and the theoretical results are verified by simulations. The proposed bigradient approach can be applied to blind separation of independent source signals from their linear mixtures.

Algorithms↗
PubMed1999

Estimating the number of clusters in multivariate data by self-organizing maps.

Determining the structure of data without prior knowledge of the number of clusters or any information about their composition is a problem of interest in many fields, such as image analysis, astrophysics, biology, etc. Partitioning a set of n patterns in a p-dimensional feature space must be done such that those in a given cluster are more similar to each other than the rest. As there are approximately Kn/K! possible ways of partitioning the patterns among K clusters, finding the best solution is very hard when n is large. The search space is increased when we have no a priori number of partitions. Although the self-organizing feature map (SOM) can be used to visualize clusters, the automation of knowledge discovery by SOM is a difficult task. This paper proposes region-based image processing methods to post-processing the U-matrix obtained after the unsupervised learning performed by SOM. Mathematical morphology is applied to identify regions of neurons that are similar. The number of regions and their labels are automatically found and they are related to the number of clusters in a multivariate data set. New data can be classified by labeling it according to the best match neuron. Simulations using data sets drawn from finite mixtures of p-variate normal densities are presented as well as related advantages and drawbacks of the method.

Algorithms↗
PubMed1999

Nonlinear system identification using a neo fuzzy neuron algorithm: electrical drive application.

This work presents a Neo-Fuzzy-Neuron algorithm for the identification of nonlinear dynamic systems at the point of view of a rotor flux observer. The algorithm training is on-line, has low computational cost, does not require previous training and its convergence in one step is proved. The gradient descent method is used for its weights adjustment. Simulation and experimental results demonstrate the effectiveness of the algorithm for flux observer of induction motor drive system.

Algorithms↗
PubMed2004

The brain-computer: origin of the idea and progress in its realization.

The Brain-Computer is a physical analogue of a real organism which uses both a brain-inspired memory-based architecture and an output-driven learning algorithm. This system can be realized by creating a scaled-down model car that learns how to drive by heuristically connecting image processing with behavior control. This study proves that learning efficiency progresses rapidly when the acquired behaviors are prioritized. We develop a small real-world device that moves about purposefully in an artificial environment. The robot uses imaging information acquired through its random actions to make a mental map. This map, then, provides the cognitive structure for acquiring necessary information for autonomous behavior.

Algorithms↗
PubMed2006

Structural modeling and analysis of signaling pathways based on Petri nets.

The purpose of this paper is to discuss how to model and analyze signaling pathways by using Petri net. Firstly, we propose a modeling method based on Petri net by paying attention to the molecular interactions and mechanisms. Then, we introduce a new notion "activation transduction component" in order to describe an enzymic activation process of reactions in signaling pathways and shows its correspondence to a so-called elementary T-invariant in the Petri net models. Further, we design an algorithm to effectively find basic enzymic activation processes by obtaining a series of elementary T-invariants in the Petri net models. Finally, we demonstrate how our method is practically used in modeling and analyzing signaling pathway mediated by thrombopoietin as an example.

Algorithms↗
PubMed2006

Complete functional characterization of sensory neurons by system identification.

System identification is a growing approach to sensory neurophysiology that facilitates the development of quantitative functional models of sensory processing. This approach provides a clear set of guidelines for combining experimental data with other knowledge about sensory function to obtain a description that optimally predicts the way that neurons process sensory information. This prediction paradigm provides an objective method for evaluating and comparing computational models. In this chapter we review many of the system identification algorithms that have been used in sensory neurophysiology, and we show how they can be viewed as variants of a single statistical inference problem. We then review many of the practical issues that arise when applying these methods to neurophysiological experiments: stimulus selection, behavioral control, model visualization, and validation. Finally we discuss several problems to which system identification has been applied recently, including one important long-term goal of sensory neuroscience: developing models of sensory systems that accurately predict neuronal responses under completely natural conditions.

Animals↗
PubMed2003

How are complex cell properties adapted to the statistics of natural stimuli?

Sensory areas should be adapted to the properties of their natural stimuli. What are the underlying rules that match the properties of complex cells in primary visual cortex to their natural stimuli? To address this issue, we sampled movies from a camera carried by a freely moving cat, capturing the dynamics of image motion as the animal explores an outdoor environment. We use these movie sequences as input to simulated neurons. Following the intuition that many meaningful high-level variables, e.g., identities of visible objects, do not change rapidly in natural visual stimuli, we adapt the neurons to exhibit firing rates that are stable over time. We find that simulated neurons, which have optimally stable activity, display many properties that are observed for cortical complex cells. Their response is invariant with respect to stimulus translation and reversal of contrast polarity. Furthermore, spatial frequency selectivity and the aspect ratio of the receptive field quantitatively match the experimentally observed characteristics of complex cells. Hence, the population of complex cells in the primary visual cortex can be described as forming an optimally stable representation of natural stimuli.

Animals↗
PubMed2002

The reliability of the stochastic active rotator.

The reliability of firing of excitable-oscillating systems is studied through the response of the active rotator, a neuronal model evolving on the unit circle, to white gaussian noise. A stochastic return map is introduced that captures the behavior of the model. This map has two fixed points: one stable and the other unstable. Iterates of all initial conditions except the unstable point tend to the stable fixed point for almost all input realizations. This means that to a given input realization, there corresponds a unique asymptotic response. In this way, repetitive stimulation with the same segment of noise realization evokes, after possibly a transient time, the same response in the active rotator. In other words, this model responds reliably to such inputs. It is argued that this results from the nonuniform motion of the active rotator around the unit circle and that similar results hold for other neuronal models whose dynamics can be approximated by phase dynamics similar to the active rotator.

Computer Simulation↗
PubMed2002

Factorial hidden Markov models and the generalized backfitting algorithm.

Previous researchers developed new learning architectures for sequential data by extending conventional hidden Markov models through the use of distributed state representations. Although exact inference and parameter estimation in these architectures is computationally intractable, Ghahramani and Jordan (1997) showed that approximate inference and parameter estimation in one such architecture, factorial hidden Markov models (FHMMs), is feasible in certain circumstances. However, the learning algorithm proposed by these investigators, based on variational techniques, is difficult to understand and implement and is limited to the study of real-valued data sets. This chapter proposes an alternative method for approximate inference and parameter estimation in FHMMs based on the perspective that FHMMs are a generalization of a well-known class of statistical models known as generalized additive models (GAMs; Hastie & Tibshirani, 1990). Using existing statistical techniques for GAMs as a guide, we have developed the generalized backfitting algorithm. This algorithm computes customized error signals for each hidden Markov chain of an FHMM and then trains each chain one at a time using conventional techniques from the hidden Markov models literature. Relative to previous perspectives on FHMMs, we believe that the viewpoint taken here has a number of advantages. First, it places FHMMs on firm statistical foundations by relating them to a class of models that are well studied in the statistics community, yet it generalizes this class of models in an interesting way. Second, it leads to an understanding of how FHMMs can be applied to many different types of time-series data, including Bernoulli and multinomial data, not just data that are real valued. Finally, it leads to an effective learning procedure for FHMMs that is easier to understand and easier to implement than existing learning procedures. Simulation results suggest that FHMMs trained with the generalized backfitting algorithm are a practical and powerful tool for analyzing sequential data.

Algorithms↗
PubMed2004

A new concept for separability problems in blind source separation.

The goal of blind source separation (BSS) lies in recovering the original independent sources of a mixed random vector without knowing the mixing structure. A key ingredient for performing BSS successfully is to know the indeterminacies of the problem-that is, to know how the separating model relates to the original mixing model (separability). For linear BSS, Comon (1994) showed using the Darmois-Skitovitch theorem that the linear mixing matrix can be found except for permutation and scaling. In this work, a much simpler, direct proof for linear separability is given. The idea is based on the fact that a random vector is independent if and only if the Hessian of its logarithmic density (resp. characteristic function) is diagonal everywhere. This property is then exploited to propose a new algorithm for performing BSS. Furthermore, first ideas of how to generalize separability results based on Hessian diagonalization to more complicated nonlinear models are studied in the setting of postnonlinear BSS.

Algorithms↗