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 1,207 records · Page 67Linked to original sources
PubMed1999

Acoustic transient classification with a template correlation processor.

I present an architecture for acoustic pattern classification using trinary-trinary template correlation. In spite of its computational simplicity, the algorithm and architecture represent a method which greatly reduces bandwidth of the input, storage requirements of the classifier memory, and power consumption of the system without compromising classification accuracy. The linear system should be amenable to training using recently-developed methods such as Independent Component Analysis (ICA), and we predict that behavior will be qualitatively similar to that of structures in the auditory cortex.

Algorithms↗
PubMed1998

Automated detection of breast carcinomas not detected in a screening program.

PURPOSE: To investigate the possibility of automated detection of early signs of cancer that were not detected in a breast cancer screening program. MATERIALS AND METHODS: A set of 75 mammograms (in 65 women) with subtle circumscribed masses, stellate lesions, and architectural distortions that were not detected in a screening program by two radiologists was assembled and extended with 142 normal mammograms (contralateral mammograms in the same 65 women). An automated system for the detection of circumscribed masses and stellate lesions was applied to this set. RESULTS: In 22 (34%) of 65 cases, an early sign of cancer was detected at a specificity of one false-positive finding per image. At a specificity of three false-positive findings per image, 39 (60%) of the cancers were detected. Of the tumors that were classified as screening errors, seven (50%) were found at a specificity of 0.5 false-positive finding per image. CONCLUSION: A substantial proportion of cancers that were missed in a screening program, despite double reading, were found with this detection method at less than one false-positive finding per image.

Algorithms↗
PubMed1995

Computer simulations of morphologically reconstructed CA3 hippocampal neurons.

1. We tested several hypotheses with respect to the mechanisms and processes that control the firing characteristics and determine the spatial and temporal dynamics of intracellular Ca2+ in CA3 hippocampal neurons. In particular, we were interested to know 1) whether bursting and nonbursting behavior of CA3 neurons could be accounted for in a morphologically realistic model using a number of the known ionic conductances; 2) whether such a model is robust across different cell morphologies; 3) whether some particular nonuniform distribution of Ca2+ channels is required for bursting; and 4) whether such a model can reproduce the magnitude and spatial distribution of intracellular Ca2+ transients determined from fluorescence imaging studies and can predict reasonable intracellular Ca2+ concentration ([Ca2+]i) distribution for CA3 neurons. 2. For this purpose we have developed a highly detailed model of the distribution and densities of membrane ion channels in hippocampal CA3 bursting and nonbursting pyramidal neurons. This model reproduces both the experimentally observed firing modes and the dynamics of intracellular Ca2+. 3. The kinetics of the membrane ionic conductances are based on available experimental data. This model incorporates a single Na+ channel, three Ca2+ channels (CaN, CaL, and CaT), three Ca(2+)-independent K+ channels (KDR, KA, and KM), two Ca(2+)-dependent K+ channels (KC and KAHP), and intracellular Ca(2+)-related processes such as buffering, pumping, and radial diffusion. 4. To test the robustness of the model, we applied it to six different morphologically accurate reconstructions of CA3 hippocampal pyramidal neurons. In every neuron, Ca2+ channels, Ca(2+)-related processes, and Ca(2+)-dependent K+ channels were uniformly distributed over the entire cell. Ca(2+)-independent K+ channels were placed on the soma and the proximal apical dendrites. For each reconstructed cell we were able to reproduce bursting and nonbursting firing characteristics as well as Ca2+ transients and distributions for both somatic and synaptic stimulations. 5. Our simulation results suggest that CA3 pyramidal cell bursting behavior does not require any special distribution of Ca(2+)-dependent channels and mechanisms. Furthermore, a simple increase in the Ca(2+)-independent K+ conductances is sufficient to change the firing mode of our CA3 neurons from bursting to nonbursting. 6. The model also displays [Ca2+]i transients and distributions that are consistent with fluorescent imaging data. Peak [Ca2+]i distribution for synaptic stimulation of the nonbursting model is broader when compared with somatic stimulation. Somatic stimulation of the bursting model shows a broader distribution in [Ca2+]i when compared with the nonbursting model.(ABSTRACT TRUNCATED AT 400 WORDS)

Calcium↗
PubMed2000

Dynamic properties of recurrent inhibition in primary visual cortex: contrast and orientation dependence of contextual effects.

A fundamental feature of neural circuitry in the primary visual cortex (V1) is the existence of recurrent excitatory connections between spiny neurons, recurrent inhibitory connections between smooth neurons, and local connections between excitatory and inhibitory neurons. We modeled the dynamic behavior of intermixed excitatory and inhibitory populations of cells in V1 that receive input from the classical receptive field (the receptive field center) through feedforward thalamocortical afferents, as well as input from outside the classical receptive field (the receptive field surround) via long-range intracortical connections. A counterintuitive result is that the response of oriented cells can be facilitated beyond optimal levels when the surround stimulus is cross-oriented with respect to the center and suppressed when the surround stimulus is iso-oriented. This effect is primarily due to changes in recurrent inhibition within a local circuit. Cross-oriented surround stimulation leads to a reduction of presynaptic inhibition and a supraoptimal response, whereas iso-oriented surround stimulation has the opposite effect. This mechanism is used to explain the orientation and contrast dependence of contextual interactions in primary visual cortex: responses to a center stimulus can be both strongly suppressed and supraoptimally facilitated as a function of surround orientation, and these effects diminish as stimulus contrast decreases.

Animals↗
PubMed2001

Analyzing holistic parsers: implications for robust parsing and systematicity.

Holistic parsers offer a viable alternative to traditional algorithmic parsers. They have good generalization performance and are robust inherently. In a holistic parser, parsing is achieved by mapping the connectionist representation of the input sentence to the connectionist representation of the target parse tree directly. Little prior knowledge of the underlying parsing mechanism thus needs to be assumed. However, it also makes holistic parsing difficult to understand. In this article, an analysis is presented for studying the operations of the confluent preorder parser (CPP). In the analysis, the CPP is viewed as a dynamical system, and holistic parsing is perceived as a sequence of state transitions through its state-space. The seemingly one-shot parsing mechanism can thus be elucidated as a step-by-step inference process, with the intermediate parsing decisions being reflected by the states visited during parsing. The study serves two purposes. First, it improves our understanding of how grammatical errors are corrected by the CPP. The occurrence of an error in a sentence will cause the CPP to deviate from the normal track that is followed when the original sentence is parsed. But as the remaining terminals are read, the two trajectories will gradually converge until finally the correct parse tree is produced. Second, it reveals that having systematic parse tree representations alone cannot guarantee good generalization performance in holistic parsing. More important, they need to be distributed in certain useful locations of the representational space. Sentences with similar trailing terminals should have their corresponding parse tree representations mapped to nearby locations in the representational space. The study provides concrete evidence that encoding the linearized parse trees as obtained via preorder traversal can satisfy such a requirement.

Algorithms↗
PubMed2002

Representation and extrapolation in multilayer perceptrons.

To give an adequate explanation of cognition and perform certain practical tasks, connectionist systems must be able to extrapolate. This work explores the relationship between input representation and extrapolation, using simulations of multilayer perceptrons trained to model the identity function. It has been discovered that representation has a marked effect on extrapolation.

Cognition↗
PubMed2005

Estimation and marginalization using the Kikuchi approximation methods.

In this letter, we examine a general method of approximation, known as the Kikuchi approximation method, for finding the marginals of a product distribution, as well as the corresponding partition function. The Kikuchi approximation method defines a certain constrained optimization problem, called the Kikuchi problem, and treats its stationary points as approximations to the desired marginals. We show how to associate a graph to any Kikuchi problem and describe a class of local message-passing algorithms along the edges of any such graph, which attempt to find the solutions to the problem. Implementation of these algorithms on graphs with fewer edges requires fewer operations in each iteration. We therefore characterize minimal graphs for a Kikuchi problem, which are those with the minimum number of edges. We show with empirical results that these simpler algorithms often offer significant savings in computational complexity, without suffering a loss in the convergence rate. We give conditions for the convexity of a given Kikuchi problem and the exactness of the approximations in terms of the loops of the minimal graph. More precisely, we show that if the minimal graph is cycle free, then the Kikuchi approximation method is exact, and the converse is also true generically. Together with the fact that in the cycle-free case, the iterative algorithms are equivalent to the well-known belief propagation algorithm, our results imply that, generically, the Kikuchi approximation method can be exact if and only if traditional junction tree methods could also solve the problem exactly.

Algorithms↗
PubMed2001

Evolution of visual resolution constrained by a trade-off.

The evolution of visual systems is constrained by a trade-off between spatial and temporal resolution. In this article we aim at identifying the causes of the trade-off at the retinal level in both artificial and natural visual systems. We start by selecting two factors that limit the values of spatial and temporal resolution. Then we show in two experiments on the evolution of an artificial system that the two factors induce trade-off curves connecting the evolved values of spatial and temporal resolution. A comparison of the experimental results with the resolution evolved in natural visual systems leads us to the conclusion that in natural systems the same factors are responsible for the observed trade-off.

Animals↗
PubMed1996

Engineering multiversion neural-net systems.

In this paper we address the problem of constructing reliable neural-net implementations, given the assumption that any particular implementation will not be totally correct. The approach taken in this paper is to organize the inevitable errors so as to minimize their impact in the context of a multiversion system, i.e., the system functionality is reproduced in multiple versions, which together will constitute the neural-net system. The unique characteristics of neural computing are exploited in order to engineer reliable systems in the form of diverse, multiversion systems that are used together with a "decision strategy" (such as majority vote). Theoretical notions of "methodological diversity" contributing to the improvement of system performance are implemented and tested. An important aspect of the engineering of an optimal system is to overproduce the components and then choose an optimal subset. Three general techniques for choosing final system components are implemented and evaluated. Several different approaches to the effective engineering of complex multiversion systems designs are realized and evaluated to determine overall reliability as well as reliability of the overall system in comparison to the lesser reliability of component substructures.

Algorithms↗
PubMed1996

Ultrasound tissue characterization of breast biopsy specimens: expanded study.

Tissue classification by examining sets of ultrasound parameters is an elusive goal. We report analysis of measurements of ultrasound speed, attenuation and backscatter in the range 3 to 8 MHz in breast tissues at 37 C. Statistical discriminant analysis and neural net analysis were employed. Data were acquired from 24 biopsy and 7 mastectomy specimens. Best separation of the classes normal, benign, and malignant occurred in the 18 cases where two tissue classes were present in the same specimen and parameters were corrected for within-patient mean; then 85-90% of cases in test sets were correctly classified. Most errors comprised misclassified benign cases. The neural net was comparable to discriminant analysis and slightly superior in separating normal and malignant classes.

Breast↗
PubMed2004

Computational techniques for diversity analysis and compound classification.

Molecular similarity and diversity analysis has played a significant role in computer-aided drug discovery for more than a decade. Compound classification methods have also become increasingly important for the design and organization of compound databases and in silico screening. Here we review these related methodologies and discuss selected applications.

Cluster Analysis↗
PubMed1999

Infrared spectroscopy of exfoliated cervical cell specimens. Proceed with caution.

OBJECTIVE: To determine whether diagnostic information may be recovered from the infrared spectra of exfoliated cell specimens by using a novel spectral feature extraction method, in conjunction with linear and quadratic discriminant analysis, for spectral classification. STUDY DESIGN: Over 800 infrared spectra were included in the study, with corresponding clinical diagnoses based upon cytology and, when available, histology reports. Three sets of classification trials were carried out with the aim of distinguishing the spectra corresponding to normal specimens from CIN 1, 2 and 3. For each of these three cases, the procedure was to: (1) develop a set of provisional classification models using only a "training" subset of the spectra, and (2) test each provisional model by its ability to correctly predict the diagnoses on the basis of the remaining spectra. RESULTS: For optimal classification trials, training set classification accuracies were 68% for normal/CIN 1, 73% for normal/CIN 2 and 81% for normal/CIN 3; for the corresponding test sets the classification accuracies were 60%, 60% and 67%, respectively. CONCLUSION: The infrared spectra of exfoliated cervical cells carry information regarding the presence or absence of dysplasia, and that information is recoverable--albeit imperfectly at this stage--from the spectra of "real life" cell preparations.

Algorithms↗
PubMed2000

Reconstructing bifurcation diagrams of dynamical systems using measured time series.

We present an algorithm for reconstructing the bifurcation structure of a dynamical system from time series. The method consists in finding a parameterized predictor function whose bifurcation structure is similar to that of the given system. Nonlinear autoregressive (NAR) models with polynomial terms are employed as predictor functions. The appropriate terms in the NAR models are obtained using a fast orthogonal search scheme. This scheme eliminates the problem of multiparameter optimization and makes the approach robust to noise. The algorithm is applied to the reconstruction of the bifurcation diagram (BD) of a neuron model from the simulated membrane potential waveforms. The reconstructed BD captures the different behaviors of the given system. Moreover, the algorithm also works well even for a limited number of time series.

Algorithms↗
PubMed2001

Provision of data for on-line simulation.

A crucial factor for the quality and results of the on-line simulation of a municipal sewage treatment system is the provision of the requisite data in adequate quality and density. Since the measured data cannot be incorporated in a simulation model without prior processing, it should be prepared in such a way that it can be converted to the model-related input quantities. If individual input measuring signals fail, substitute value concepts must be developed which are based on the remaining information. With this it is possible to ensure the continuous provision of data. Various approaches are possible in seeking a solution to this problem. At the Wupperverband a detailed programme of investigation on the subject area of the processing of inflow data is being implemented as a component of future on-line simulation at Wuppertal-Buchenhofen STP.

Chemical Fractionation↗
PubMed2003

Learning input correlations through nonlinear temporally asymmetric Hebbian plasticity.

Triggered by recent experimental results, temporally asymmetric Hebbian (TAH) plasticity is considered as a candidate model for the biological implementation of competitive synaptic learning, a key concept for the experience-based development of cortical circuitry. However, because of the well known positive feedback instability of correlation-based plasticity, the stability of the resulting learning process has remained a central problem. Plagued by either a runaway of the synaptic efficacies or a greatly reduced sensitivity to input correlations, the learning performance of current models is limited. Here we introduce a novel generalized nonlinear TAH learning rule that allows a balance between stability and sensitivity of learning. Using this rule, we study the capacity of the system to learn patterns of correlations between afferent spike trains. Specifically, we address the question of under which conditions learning induces spontaneous symmetry breaking and leads to inhomogeneous synaptic distributions that capture the structure of the input correlations. To study the efficiency of learning temporal relationships between afferent spike trains through TAH plasticity, we introduce a novel sensitivity measure that quantifies the amount of information about the correlation structure in the input, a learning rule capable of storing in the synaptic weights. We demonstrate that by adjusting the weight dependence of the synaptic changes in TAH plasticity, it is possible to enhance the synaptic representation of temporal input correlations while maintaining the system in a stable learning regime. Indeed, for a given distribution of inputs, the learning efficiency can be optimized.

Action Potentials↗