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 1,549 records · Page 86Linked to original sources
PubMed2000

ANN-Spec: a method for discovering transcription factor binding sites with improved specificity.

This work describes ANN-Spec, a machine learning algorithm and its application to discovering un-gapped patterns in DNA sequence. The approach makes use of an Artificial Neural Network and a Gibbs sampling method to define the Specificity of a DNA-binding protein. ANN-Spec searches for the parameters of a simple network (or weight matrix) that will maximize the specificity for binding sequences of a positive set compared to a background sequence set. Binding sites in the positive data set are found with the resulting weight matrix and these sites are then used to define a local multiple sequence alignment. Training complexity is O(lN) where l is the width of the pattern and N is the size of the positive training data. A quantitative comparison of ANN-Spec and a few related programs is presented. The comparison shows that ANN-Spec finds patterns of higher specificity when training with a background data set. The program and documentation are available from the authors for UNIX systems.

Algorithms↗
PubMed2006

Programmable logic construction kits for hyper-real-time neuronal modeling.

Programmable logic designs are presented that achieve exact integration of leaky integrate-and-fire soma and dynamical synapse neuronal models and incorporate spike-time dependent plasticity and axonal delays. Highly accurate numerical performance has been achieved by modifying simpler forward-Euler-based circuitry requiring minimal circuit allocation, which, as we show, behaves equivalently to exact integration. These designs have been implemented and simulated at the behavioral and physical device levels, demonstrating close agreement with both numerical and analytical results. By exploiting finely grained parallelism and single clock cycle numerical iteration, these designs achieve simulation speeds at least five orders of magnitude faster than the nervous system, termed here hyper-real-time operation, when deployed on commercially available field-programmable gate array (FPGA) devices. Taken together, our designs form a programmable logic construction kit of commonly used neuronal model elements that supports the building of large and complex architectures of spiking neuron networks for real-time neuromorphic implementation, neurophysiological interfacing, or efficient parameter space investigations.

Action Potentials↗
PubMedDate not supplied

[Study of giant depolarizing activity in the neonatal hippocampal neurones].

Spontaneous oscillatory activity is a general feature of developing neural networks. Early in postnatal development, spontaneous network-driven events, termed giant depolarizing potentials (GDPs), occur synchronously over the entire hippocampus. By performing simulation of hippocampal network with using physiology parameters of the neurons and its network from the present experiments and literature dates, we investigated the participation of the different components of network in the generation of GDPs. Comparing the results of the model and in vitro experiments we conclude that are necessary for the GDP generation involvement the activation of GABAergic, glutamatergic inputs and perhaps gap junction.

Animals↗
PubMed1992

Limits on alpha-helix prediction with neural network models.

Using a backpropagation neural network model we have found a limit for secondary structure prediction from local sequence. By including only sequences from whole alpha-helix and non-alpha-helix structures in our training and test sets--sequences spanning boundaries between these two structures were excluded--it was possible to investigate directly the relationship between sequence and structure for alpha-helix. A group of non-alpha-helix sequences, that was disrupting overall prediction success, was indistinguishable to the network from alpha-helix sequences. These sequences were found to occur at regions adjacent to the termini of alpha-helices with statistical significance, suggesting that potentially longer alpha-helices are disrupted by global constraints. Some of these regions spanned more than 20 residues. On these whole structure sequences, 10 residues in length, a comparatively high prediction success of 78% with a correlation coefficient of 0.52 was achieved. In addition, the structure of the input space, the distribution of beta-sheet in this space, and the effect of segment length were also investigated.

Amino Acid Sequence↗
PubMed2005

Spatiotemporal Hopfield neural cube for diagnosing recurrent nasal papilloma.

Gadolinium-enhanced magnetic resonance imaging (MRI) is widely used to detect recurrent nasal tumours. A specifically designed two-layer Hopfield neural network, called the spatiotemporal Hopfield neural cube (SHNC), is presented, to be used for detecting recurrent nasal papilloma. Differing from conventional, two-dimensional Hopfield neural networks, the SHNC extends the one-layer, two-dimensional Hopfield network in the original image plane into a two-layer, three-dimensional (3D) Hopfield network with pixel classification implemented in its third dimension. With extended 3D architecture, the network is able to use each pixel's spatial information in a pixel labelling procedure. Because the SHNC takes pixel spatial information into consideration, the effects of tiny detail or noise are removed. As a result, the drawback of disconnected fractions can be avoided. Furthermore, owing to the incorporation of competitive learning rules to update neuron states, to avoid the problem of having to satisfy strong constraints, the convergence of the network was improved. In addition, a more accurate signal-time curve, the relative intensity change (RIC), was adopted to represent the gadolinium-enhanced MRI temporal information, and the RIC curves of recurrent nasal papilloma were incorporated into the SHNC. The experimental results showed that the SHNC could obtain a more appropriate, precise position of recurrent nasal papilloma than the k-means, principal components analysis (PCA) or Eigenimage-filtering methods. The average sensitivity and specificity of the 26 cases were 0.9998 and 0.9961, respectively. These values demonstrate the effectiveness of the proposed technique.

Humans↗
PubMedDate not supplied

The neural network as a tool for multispectral interpretation.

A neural network which utilized data from the infrared spectra, carbon-13 NMR spectra, and molecular formulas of organic compounds was developed. The network, which had one layer of hidden units, was trained by backpropagation; network parameters were determined by a simplex optimization procedure. A database of 1560 compounds was used for training and testing. The trained network was able to identify with high accuracy the presence of a broad range of substructural features present in the compounds. The number of features identified and the accuracy were significantly greater as compared with networks using data from a single form of spectroscopy. The results have significance for the SESAMI computer-enhanced structure elucidation system.

Computers↗
PubMed2001

Noise, regularizers, and unrealizable scenarios in online learning from restricted training sets.

We study the dynamics of online learning in multilayer neural networks where training examples are sampled with repetition and where the number of examples scales with the number of network weights. The analysis is carried out using the dynamical replica method aimed at obtaining a closed set of coupled equations for a set of macroscopic variables from which both training and generalization errors can be calculated. We focus on scenarios whereby training examples are corrupted by additive Gaussian output noise and regularizers are introduced to improve the network performance. The dependence of the dynamics on the noise level, with and without regularizers, is examined, as well as that of the asymptotic values obtained for both training and generalization errors. We also demonstrate the ability of the method to approximate the learning dynamics in structurally unrealizable scenarios. The theoretical results show good agreement with those obtained from computer simulations.

Algorithms↗
PubMed1996

A self-organizing model of "color blob" formation.

This paper explores the possibility that the formation of color blobs in primate striate cortex can be partly explained through the process of activity-based self-organization. We present a simulation of a highly simplified model of visual processing along the parvocellular pathway, that combines precortical color processing, excitatory and inhibitory cortical interactions, and Hebbian learning. The model self-organizes in response to natural color images and develops islands of unoriented, color-selective cells within a sea of contrast-sensitive, orientation-selective cells. By way of understanding this topography, a principal component analysis of the color inputs presented to the network reveals that the optimal linear coding of these inputs keeps color information and contrast information separate.

Animals↗
PubMed2006

How inhibitory oscillations can train neural networks and punish competitors.

We present a new learning algorithm that leverages oscillations in the strength of neural inhibition to train neural networks. Raising inhibition can be used to identify weak parts of target memories, which are then strengthened. Conversely, lowering inhibition can be used to identify competitors, which are then weakened. To update weights, we apply the Contrastive Hebbian Learning equation to successive time steps of the network. The sign of the weight change equation varies as a function of the phase of the inhibitory oscillation. We show that the learning algorithm can memorize large numbers of correlated input patterns without collapsing and that it shows good generalization to test patterns that do not exactly match studied patterns.

Algorithms↗
PubMed1993

CaseLog: semantic network interface to a student computer-based patient record system.

We have developed a computer program called CaseLog, which serves as an exemplary, computer-based patient record (CPR) system. The program allows for the introduction of the students to issues unique to patient record systems. These include record security, unique patient identifiers, and the use of controlled vocabularies. A particularly challenging aspect of the development of this program was allowing for student entry of controlled vocabulary terms. There were four goals we wished to achieve: students should be able to find the terms they are looking for; once a term has been found, it should be easy to find contextually related terms; it should be easy to determine that a sought-for term is not in the vocabulary; and the structure of the vocabulary should be dynamically altered by contextual information to allow its use for a variety of purposes. We chose a semantic network for our vocabulary structure. Within the processing power of the equipment we were working with, we achieved our goals. This paper will describe the development of the vocabulary, the design of the CaseLog program, and the feedback from student users of the program.

Computer Systems↗
PubMed1995

Synchrony in excitatory neural networks.

Synchronization properties of fully connected networks of identical oscillatory neurons are studied, assuming purely excitatory interactions. We analyze their dependence on the time course of the synaptic interaction and on the response of the neurons to small depolarizations. Two types of responses are distinguished. In the first type, neurons always respond to small depolarization by advancing the next spike. In the second type, an excitatory postsynaptic potential (EPSP) received after the refractory period delays the firing of the next spike, while an EPSP received at a later time advances the firing. For these two types of responses we derive general conditions under which excitation destabilizes in-phase synchrony. We show that excitation is generally desynchronizing for neurons with a response of type I but can be synchronizing for responses of type II when the synaptic interactions are fast. These results are illustrated on three models of neurons: the Lapicque integrate-and-fire model, the model of Connor et al., and the Hodgkin-Huxley model. The latter exhibits a type II response, at variance with the first two models, that have type I responses. We then examine the consequences of these results for large networks, focusing on the states of partial coherence that emerge. Finally, we study the Lapicque model and the model of Connor et al. at large coupling and show that excitation can be desynchronizing even beyond the weak coupling regime.

Computer Simulation↗
PubMed2006

Quantification of atherosclerotic plaque components using in vivo MRI and supervised classifiers.

In this work we aimed to study the possibility of using supervised classifiers to quantify the main components of carotid atherosclerotic plaque in vivo on the basis of multisequence MRI data. MRI data consisting of five MR weightings were obtained from 25 symptomatic subjects. Histological micrographs of endarterectomy specimens from the 25 carotids were used as a standard of reference for training and evaluation. The set of subjects was divided in a training set (12 subjects) and an evaluation set (13 subjects). Four different classifiers and two human MRI readers determined the percentages of calcified tissue, fibrous tissue, lipid core, and intraplaque hemorrhage on the subject level for all subjects in the evaluation set. Quantification of the relatively small amounts of calcium could not be done with statistical significance by either the classifiers or the MRI readers. For the other tissues a simple Bayesian classifier (Bayes) performed better than the other classifiers and the MRI readers. All classifiers performed better than the MRI readers in quantifying the sum of hemorrhage and lipid proportions. The MRI readers overestimated the hemorrhage proportions and tended to underestimate the lipid proportions. In conclusion, this pilot study demonstrates the benefits of algorithmic classifiers for quantifying plaque components.

Algorithms↗
PubMed1994

Computer models of the brain--how far can they take us?

The recent developments in computer capacity and algorithms, together with a tremendous growth of data in neuroscience have dramatically improved the possibilities of modeling and simulating certain brain structures and activities with a considerable degree of realism. Although there is still a long way to go, some claim that we will one day be able to create artificial "brains" with similar capacity to the human brain, perhaps even surpassing it. Here we focus on these perspectives, discussing the potentials and limitations of today's computer models, and how far they might be able to take us.

Brain↗
PubMed2005

Automated high-throughput nanoliter-scale protein crystallization screening.

A highly efficient method is developed for automated high-throughput screening of nanoliter-scale protein crystallization. The system integrates liquid dispensing, crystallization and detection. The automated liquid dispensing system handles nanoliters of protein and various combinations of precipitants in parallel to access diverse regions of the phase diagram. A new detection scheme, native fluorescence, with complementary visible-light detection is employed for monitoring the progress of crystallization. This detection mode can distinguish protein crystals from inorganic crystals in a nondestructive manner. A gas-permeable membrane covering the microwells simplifies evaporation rate control and probes extended conditions in the phase diagram. The system was successfully demonstrated for the screening of lysozyme crystallization under 81 different conditions.

Automation↗
PubMed2004

Contour integration and segmentation with self-organized lateral connections.

Contour integration in low-level vision is believed to occur based on lateral interaction between neurons with similar orientation tuning. How such interactions could arise in the brain has been an open question. Our model suggests that the interactions can be learned through input-driven self-organization, i.e., through the same mechanism that underlies many other developmental and functional phenomena in the visual cortex. The model also shows how synchronized firing mediated by these lateral connections can represent the percept of a contour, resulting in performance similar to that of human contour integration. The model further demonstrates that contour integration performance can differ in different parts of the visual field, depending on what kinds of input distributions they receive during development. The model thus grounds an important perceptual phenomenon onto detailed neural mechanisms so that various structural and functional properties can be measured and predictions can be made to guide future experiments.

Animals↗
PubMed2006

A visual model for object detection based on active contours and level-set method.

A visual model for object detection is proposed. In order to make the detection ability comparable with existing technical methods for object detection, an evolution equation of neurons in the model is derived from the computational principle of active contours. The hierarchical structure of the model emerges naturally from the evolution equation. One drawback involved with initial values of active contours is alleviated by introducing and formulating convexity, which is a visual property. Numerical experiments show that the proposed model detects objects with complex topologies and that it is tolerant of noise. A visual attention model is introduced into the proposed model. Other simulations show that the visual properties of the model are consistent with the results of psychological experiments that disclose the relation between figure-ground reversal and visual attention. We also demonstrate that the model tends to perceive smaller regions as figures, which is a characteristic observed in human visual perception.

Animals↗