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 1,603 records · Page 89Linked to original sources
PubMed2003

The neural computation of the aperture problem: an iterative process.

The aperture problem is defined as one of integrating motion information from inside and outside of the aperture, and determination of the true direction of motion of a line. Much is known about it and many models have been proposed for its neural mechanisms. However, it is still a matter of debate whether the brain solves the problem by using only feed-forward neural connections, also known as the one-shot algorithm, or by using the iterative algorithm while utilizing feedback as well as horizontal neural connections. Here we show unequivocal evidence for the latter model. The model was tested using critically designed psychophysical experiments and the results were perfectly in line with the psychophysical performance of the observers.

Algorithms↗
PubMed2006

Implementing online natural gradient learning: problems and solutions.

The online natural gradient learning is an efficient algorithm to resolve the slow learning speed and poor performance of the standard gradient descent method. However, there are several problems to implement this algorithm. In this paper, we proposed a new algorithm to solve these problems and then compared the new algorithm with other known algorithms for online learning, including Almeida-Langlois-Amaral-Plakhov algorithm (ALAP), Vario-eta, local adaptive learning rate and learning with momentum etc., using sample data sets from Proben1 and normalized handwritten digits, automatically scanned from envelopes by the U.S. Postal Services. The strong and weak points of these algorithms were analyzed and tested empirically. We found out that using the online training error as the criterion to determine whether the learning rate should be changed or not is not appropriate and our new algorithm has better performance than other existing online algorithms.

Algorithms↗
PubMed2006

Modulated Hebb-Oja learning rule--a method for principal subspace analysis.

This paper presents analysis of the recently proposed modulated Hebb-Oja (MHO) method that performs linear mapping to a lower-dimensional subspace. Principal component subspace is the method that will be analyzed. Comparing to some other well-known methods for yielding principal component subspace (e.g., Oja's Subspace Learning Algorithm), the proposed method has one feature that could be seen as desirable from the biological point of view--synaptic efficacy learning rule does not need the explicit information about the value of the other efficacies to make individual efficacy modification. Also, the simplicity of the "neural circuits" that perform global computations and a fact that their number does not depend on the number of input and output neurons, could be seen as good features of the proposed method.

Algorithms↗
PubMed2006

Spiking perceptrons.

A more plausible biological version of the traditional perceptron is presented here with a learning rule which enables training of the neuron on nonlinear tasks. Three different models are introduced with varying inhibitory and excitatory synaptic connections. Using the derived learning rule, a single neuron is trained to successfully classify the XOR problem.

Action Potentials↗
PubMed2006

Combining genetic algorithms and Lyapunov-based adaptation for online design of fuzzy controllers.

This paper proposes a hybrid approach for the design of adaptive fuzzy controllers (FCs) in which two learning algorithms with different characteristics are merged together to obtain an improved method. The approach combines a genetic algorithm (GA), devised to optimize all the configuration parameters of the FC, including the number of membership functions and rules, and a Lyapunov-based adaptation law performing a local tuning of the output singletons of the controller, and guaranteeing the stability of each new controller investigated by the GA. The effectiveness of the proposed method is confirmed using both numerical simulations on a known case study and experiments on a nonlinear hardware benchmark.

Algorithms↗
PubMed2001

A fast and convergent stochastic MLP learning algorithm.

We propose a stochastic learning algorithm for multilayer perceptrons of linear-threshold function units, which theoretically converges with probability one and experimentally exhibits 100% convergence rate and remarkable speed on parity and classification problems with typical generalization accuracy. For learning the n bit parity function with n hidden units, the algorithm converged on all the trials we tested (n=2 to 12) after 5.8 x 4.1(n) presentations for 0.23 x 4.0(n-6) seconds on a 533MHz Alpha 21164A chip on average, which is five to ten times faster than Levenberg-Marquardt algorithm with restarts. For a medium size classification problem known as Thyroid in UCI repository, the algorithm is faster in speed and comparative in generalization accuracy than the standard backpropagation and Levenberg-Marquardt algorithms.

Algorithms↗
PubMed2003

Wavelet-like receptive fields emerges by non-linear minimization of neuron error.

Redundancy reduction as a form of neural coding has been since the early sixties a topic of large research interest. A number of strategies has been proposed, but the one which is attracting most attention recently assumes that this coding is carried out so that the output signals are mutually independent. In this work we go one step further and suggest an strategy to deal also with non-orthogonal signals (i.e., "dependent" signals). Moreover, instead of working with the usual squared error, we design a neuron where the non-linearity is operating on the error. It is computationally more economic and, importantly, the permutation/scaling problem is avoided. The framework is given with a biological background, as we avocate throughout the manuscript that the algorithm fits well the single neuron and redundancy reduction doctrine. Moreover, we show that wavelet-like receptive fields emerges from natural images processed by this algorithm.

Algorithms↗
PubMed2004

Model-free functional MRI analysis using topographic independent component analysis.

Data-driven fMRI analysis techniques include independent component analysis (ICA) and different types of clustering in the temporal domain. Since each of these methods has its particular strengths, it is natural to look for an approach that unifies Kohonen's self-organizing map and ICA. This is given by the topographic independent component analysis. While achieved by a slight modification of the ICA model, it can be at the same time used to define a topographic order (clusters) between the components, and thus has the usual computational advantages associated with topographic maps. In this contribution, we can show that when applied to fMRI analysis it outperforms FastICA.

Algorithms↗
PubMedDate not supplied

The role of global and feature based information in gender classification of faces: a comparison of human performance and computational models.

Most computational models for gender classification use global information (the full face image) giving equal weight to the whole face area irrespective of the importance of the internal features. Here, we use a global and feature based representation of face images that includes both global and featural information. We use dimensionality reduction techniques and a support vector machine classifier and show that this method performs better than either global or feature based representations alone. We also present results of human subjects performance on gender classification task and evaluate how the different dimensionality reduction techniques compare with human subjects performance. The results support the psychological plausibility of the global and feature based representation.

Algorithms↗
PubMedDate not supplied

Detection of laboratory false negative smears by the PAPNET cytologic screening system.

OBJECTIVE: To evaluate the ability of PAPNET-assisted screening to identify abnormal slides that had originally been reported as negative on manual screening. STUDY DESIGN: One hundred ninety-five abnormal slides were seeded into 20,000 slides that had been assessed as showing no abnormality on two occasions by manual screening. All slides were submitted for PAPNET review and the tiles assessed by trained cytotechnologists. RESULTS: With a single assessment of the PAPNET tiles and when the prevalence of seeded abnormality was around 1%, only 44% of the seeded abnormal slides were recognized as abnormal. With multiple independent assessments and by increasing the prevalence of abnormality to 81%, 83% of the seeded abnormalities were recognized by at least one of three reviewing cytotechnologists. This increase in sensitivity appeared to be associated with a state of relative hyperalertness in the reviewing cytotechnologists. CONCLUSION: The sensitivity of a PAPNET-assisted review was < 100% for the detection of seeded abnormal slides. Altering the format of presentation of information to the cytotechnologist may result in improved sensitivity.

Algorithms↗
PubMed2001

A spike-train probability model.

Poisson processes usually provide adequate descriptions of the irregularity in neuron spike times after pooling the data across large numbers of trials, as is done in constructing the peristimulus time histogram. When probabilities are needed to describe the behavior of neurons within individual trials, however, Poisson process models are often inadequate. In principle, an explicit formula gives the probability density of a single spike train in great generality, but without additional assumptions, the firing-rate intensity function appearing in that formula cannot be estimated. We propose a simple solution to this problem, which is to assume that the time at which a neuron fires is determined probabilistically by, and only by, two quantities: the experimental clock time and the elapsed time since the previous spike. We show that this model can be fitted with standard methods and software and that it may used successfully to fit neuronal data.

Animals↗
PubMed2004

A learning rule for local synaptic interactions between excitation and shunting inhibition.

The basic requirement for direction selectivity is a nonlinear interaction between two different inputs in space-time. In some models, the interaction is hypothesized to occur between excitation and inhibition of the shunting type in the neuron's dendritic tree. How can the required spatial specificity be acquired in an unsupervised manner? We here propose an activity-based, local learning model that can account for direction selectivity in visual cortex based on such a local veto operation and that depends on synaptically induced changes in intracellular calcium concentration. Our biophysical simulations suggest that a model cell with our learning algorithm can develop direction selectivity organically after unsupervised training. The learning rule is also applicable to a neuron with multiple-direction-selective subunits and to a pair of cells with opposite-direction selectivities and is stable under different starting conditions, delays, and velocities.

Algorithms↗
PubMed2000

A genetic model: analysis and application to MAXSAT.

In this paper, a genetic model based on the operations of recombination and mutation is studied and applied to combinatorial optimization problems. Results are: 1. The equations of the deterministic dynamics in the thermodynamic limit (infinite populations) are derived and, for a sufficiently small mutation rate, the attractors are characterized; 2. A general approximation algorithm for combinatorial optimization problems is designed. The algorithm is applied to the Max Ek-Sat problem, and the quality of the solution is analyzed. It is proved to be optimal for k > or = 3 with respect to the worst case analysis; for Max E3-Sat the average case performances are experimentally compared with other optimization techniques.

Algorithms↗
PubMed2005

The hierarchical fair competition (HFC) framework for sustainable evolutionary algorithms.

Many current Evolutionary Algorithms (EAs) suffer from a tendency to converge prematurely or stagnate without progress for complex problems. This may be due to the loss of or failure to discover certain valuable genetic material or the loss of the capability to discover new genetic material before convergence has limited the algorithm's ability to search widely. In this paper, the Hierarchical Fair Competition (HFC) model, including several variants, is proposed as a generic framework for sustainable evolutionary search by transforming the convergent nature of the current EA framework into a non-convergent search process. That is, the structure of HFC does not allow the convergence of the population to the vicinity of any set of optimal or locally optimal solutions. The sustainable search capability of HFC is achieved by ensuring a continuous supply and the incorporation of genetic material in a hierarchical manner, and by culturing and maintaining, but continually renewing, populations of individuals of intermediate fitness levels. HFC employs an assembly-line structure in which subpopulations are hierarchically organized into different fitness levels, reducing the selection pressure within each subpopulation while maintaining the global selection pressure to help ensure the exploitation of the good genetic material found. Three EAs based on the HFC principle are tested - two on the even-10-parity genetic programming benchmark problem and a real-world analog circuit synthesis problem, and another on the HIFF genetic algorithm (GA) benchmark problem. The significant gain in robustness, scalability and efficiency by HFC, with little additional computing effort, and its tolerance of small population sizes, demonstrates its effectiveness on these problems and shows promise of its potential for improving other existing EAs for difficult problems. A paradigm shift from that of most EAs is proposed: rather than trying to escape from local optima or delay convergence at a local optimum, HFC allows the emergence of new optima continually in a bottom-up manner, maintaining low local selection pressure at all fitness levels, while fostering exploitation of high-fitness individuals through promotion to higher levels.

Algorithms↗
PubMed2006

Temporal decoding by phase-locked loops: unique features of circuit-level implementations and their significance for vibrissal information processing.

Rhythmic active touch, such as whisking, evokes a periodic reference spike train along which the timing of a novel stimulus, induced, for example, when the whiskers hit an external object, can be interpreted. Previous work supports the hypothesis that the whisking-induced spike train entrains a neural implementation of a phase-locked loop (NPLL) in the vibrissal system. Here we extend this work and explore how the entrained NPLL decodes the delay of the novel, contact-induced stimulus and facilitates object localization. We consider two implementations of NPLLs, which are based on a single neuron or a neural circuit, respectively, and evaluate the resulting temporal decoding capabilities. Depending on the structure of the NPLL, it can lock in either a phase- or co-phase-sensitive mode, which is sensitive to the timing of the input with respect to the beginning of either the current or the next cycle, respectively. The co-phase-sensitive mode is shown to be unique to circuit-based NPLLs. Concentrating on temporal decoding in the vibrissal system of rats, we conclude that both the nature of the information processing task and the response characteristics suggest that the computation is sensitive to the co-phase. Consequently, we suggest that the underlying thalamocortical loop should implement a circuit-based NPLL.

Animals↗
PubMed2006

Improved alignment quality by combining evolutionary information, predicted secondary structure and self-organizing maps.

BACKGROUND: Protein sequence alignment is one of the basic tools in bioinformatics. Correct alignments are required for a range of tasks including the derivation of phylogenetic trees and protein structure prediction. Numerous studies have shown that the incorporation of predicted secondary structure information into alignment algorithms improves their performance. Secondary structure predictors have to be trained on a set of somewhat arbitrarily defined states (e.g. helix, strand, coil), and it has been shown that the choice of these states has some effect on alignment quality. However, it is not unlikely that prediction of other structural features also could provide an improvement. In this study we use an unsupervised clustering method, the self-organizing map, to assign sequence profile windows to "structural states" and assess their use in sequence alignment. RESULTS: The addition of self-organizing map locations as inputs to a profile-profile scoring function improves the alignment quality of distantly related proteins slightly. The improvement is slightly smaller than that gained from the inclusion of predicted secondary structure. However, the information seems to be complementary as the two prediction schemes can be combined to improve the alignment quality by a further small but significant amount. CONCLUSION: It has been observed in many studies that predicted secondary structure significantly improves the alignments. Here we have shown that the addition of self-organizing map locations can further improve the alignments as the self-organizing map locations seem to contain some information that is not captured by the predicted secondary structure.

Computational Biology↗