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 1,081 records · Page 60Linked to original sources

PubMed2005

Memorization and association on a realistic neural model.

A central open question of computational neuroscience is to identify the data structures and algorithms that are used in mammalian cortex to support successive acts of the basic cognitive tasks of memorization and association. This letter addresses the simultaneous challenges of realizing these two distinct tasks with the same data structure, and doing so while respecting the following four basic quantitative parameters of cortex: the neuron number, the synapse number, the synapse strengths, and the switching times. Previous work has not succeeded in reconciling these opposing constraints, the low values of synapse strengths that are typically observed experimentally having contributed a particular obstacle. In this article, we describe a computational scheme that supports both memory formation and association and is feasible on networks of model neurons that respect the widely observed values of the four quantitative parameters. Our scheme allows for both disjoint and shared representations. The algorithms are simple, and in one version both memorization and association require just one step of vicinal or neighborly influence. The issues of interference among the different circuits that are established, of robustness to noise, and of the stability of the hierarchical memorization process are addressed. A calculus therefore is implied for analyzing the capabilities of particular neural systems and subsystems, in terms of their basic numerical parameters.

Algorithms↗

PubMed2005

Identification of large-scale networks in the brain using fMRI.

Cognition is thought to result from interactions within large-scale networks of brain regions. Here, we propose a method to identify these large-scale networks using functional magnetic resonance imaging (fMRI). Regions belonging to such networks are defined as sets of strongly interacting regions, each of which showing a homogeneous temporal activity. Our method of large-scale network identification (LSNI) proceeds by first detecting functionally homogeneous regions. The networks of functional interconnections are then found by comparing the correlations among these regions against a model of the correlations in the noise. To test the LSNI method, we first evaluated its specificity and sensitivity on synthetic data sets. Then, the method was applied to four real data sets with a block-designed motor task. The LSNI method correctly recovered the regions whose temporal activity was locked to the stimulus. In addition, it detected two other main networks highly reproducible across subjects, whose activity was dominated by slow fluctuations (0-0.1 Hz). One was located in medial and dorsal regions, and mostly overlapped the "default" network of the brain at rest [Greicius, M.D., Krasnow, B., Reiss, A.L., Menon, V., 2003. Functional connectivity in the resting brain: a network analysis of the default mode hypothesis. Proceedings of the National Academy of Sciences of the U.S.A. 100, 253-258]; the other was composed of lateral frontal and posterior parietal regions. The LSNI method we propose allows to detect in an exploratory and systematic way all the regions and large-scale networks activated in the working brain.

Adult↗

PubMed2002

Dynamics of Boolean networks controlled by biologically meaningful functions.

The remarkably stable dynamics displayed by randomly constructed Boolean networks is one of the most striking examples of the spontaneous emergence of self-organization in model systems composed of many interacting elements (Kauffman, S., J. theor. Biol.22, 437-467, 1969; The Origins of Order, Oxford University Press, Oxford, 1993). The dynamics of such networks is most stable for a connectivity of two inputs per element, and decreases dramatically with increasing number of connections. Whereas the simplicity of this model system allows the tracing of the dynamical trajectories, it leaves out many features of real biological connections. For instance, the dynamics has been studied in detail only for networks constructed by allowing all theoretically possible Boolean rules, whereas only a subset of them make sense in the material world. This paper analyses the effect on the dynamics of using only Boolean functions which are meaningful in a biological sense. This analysis is particularly relevant for nets with more than two inputs per element because biological networks generally appear to be more extensively interconnected. Sets of the meaningful functions were assembled for up to four inputs per element. The use of these rules results in a smaller number of distinct attractors which have a shorter length, with relatively little sensitivity to the size of the network and to the number of inputs per element. Forcing away the activator/inhibitor ratio from the expected value of 50% further enhances the stability. This effect is more pronounced for networks consisting of a majority of activators than for networks with a corresponding majority of inhibitors, indicating that the former allow the evolution of larger genetic networks. The data further support the idea of the usefulness of logical networks as a conceptual framework for the understanding of real-world phenomena.

Algorithms↗

PubMed2002

Lung cancer cell identification based on artificial neural network ensembles.

An artificial neural network ensemble is a learning paradigm where several artificial neural networks are jointly used to solve a problem. In this paper, an automatic pathological diagnosis procedure named Neural Ensemble-based Detection (NED) is proposed, which utilizes an artificial neural network ensemble to identify lung cancer cells in the images of the specimens of needle biopsies obtained from the bodies of the subjects to be diagnosed. The ensemble is built on a two-level ensemble architecture. The first-level ensemble is used to judge whether a cell is normal with high confidence where each individual network has only two outputs respectively normal cell or cancer cell. The predictions of those individual networks are combined by a novel method presented in this paper, i.e. full voting which judges a cell to be normal only when all the individual networks judge it is normal. The second-level ensemble is used to deal with the cells that are judged as cancer cells by the first-level ensemble, where each individual network has five outputs respectively adenocarcinoma, squamous cell carcinoma, small cell carcinoma, large cell carcinoma, and normal, among which the former four are different types of lung cancer cells. The predictions of those individual networks are combined by a prevailing method, i.e. plurality voting. Through adopting those techniques, NED achieves not only a high rate of overall identification, but also a low rate of false negative identification, i.e. a low rate of judging cancer cells to be normal ones, which is important in saving lives due to reducing missing diagnoses of cancer patients.

Adenocarcinoma↗

PubMed1992

Purposive behavior and cognitive mapping: a neural network model.

This study presents a real-time, biologically plausible neural network approach to purposive behavior and cognitive mapping. The system is composed of (a) an action system, consisting of a goal-seeking neural mechanism controlled by a motivational system; and (b) a cognitive system, involving a neural cognitive map. The goal-seeking mechanism displays exploratory behavior until either (a) the goal is found or (b) an adequate prediction of the goal is generated. The cognitive map built by the network is a topological map, i.e., it represents only the adjacency, but not distances or directions, between places. The network has recurrent and non-recurrent properties that allow the reading of the cognitive map without modifying it. Two types of predictions are introduced: fast-time and real-time predictions. Fast-time predictions are produced in advance of what occurs in real time, when the information stored in the cognitive map is used to predict the remote future. Real-time predictions are generated simultaneously with the occurrence of environmental events, when the information stored in the cognitive map is being updated. Computer simulations show that the network successfully describes latent learning and detour behavior in rats. In addition, simulations demonstrate that the network can be applied to problem-solving paradigms such as the Tower of Hanoi puzzle.

Animals↗

PubMed2001

A neural network approach to the outcome definition on first treatment with sertraline in a psychiatric population.

Therapy decision is one of the most important tasks clinicians have to perform in their clinical practice. The decision process requires taking into account many different factors. The Authors have proposed a neural computing approach for supporting clinical decision analysis. The mathematical model of artificial neural network (ANN) has been applied on a pool of clinical information gathered through case description freely filled by senior psychiatrists into 416 clinical charts. Sertraline, as drug for treatment, has been chosen since its clinical uses range from treatment of depression to that of many other psychiatric clinical conditions so that it has been thought to be a good candidate to this type of study. The ANN performance in forecasting successful and unsuccessful treatment cases showed an overall accuracy of classification of 97.35%. This result suggests a possible future application of this method to obtain a reliable prediction of a given psychiatric patient outcome during a specific psychopharmacological therapy, optimising the decisional making process.

Adolescent↗

PubMed1992

Chemical implementation and thermodynamics of collective neural networks.

The chemical implementation of a neuron and connections among neurons described in prior work is used to construct collective neural networks. With stated approximations, these chemical networks are reduced to networks of the Hopfield type. Chemical networks approaching a stationary or equilibrium state provide a Liapunov function with the same extremal properties as Hopfield's energy function. Numerical comparisons of chemical and Hopfield networks with small numbers (2-16) of neurons show agreement on the results of given computations.

Catalysis↗

PubMed2002

A comparative study on kernel-based probabilistic neural networks for speaker verification.

This paper compares kernel-based probabilistic neural networks for speaker verification based on 138 speakers of the YOHO corpus. Experimental evaluations using probabilistic decision-based neural networks (PDBNNs), Gaussian mixture models (GMMs) and elliptical basis function networks (EBFNs) as speaker models were conducted. The original training algorithm of PDBNNs was also modified to make PDBNNs appropriate for speaker verification. Results show that the equal error rate obtained by PDBNNs and GMMs is less than that of EBFNs (0.33% vs. 0.48%), suggesting that GMM- and PDBNN-based speaker models outperform the EBFN ones. This work also finds that the globally supervised learning of PDBNNs is able to find decision thresholds that not only maintain the false acceptance rates to a low level but also reduce their variation, whereas the ad-hoc threshold-determination approach used by the EBFNs and GMMs causes a large variation in the error rates. This property makes the performance of PDBNN-based systems more predictable.

Algorithms↗

PubMed2003

Associative memory design using overlapping decomposition and generalized brain-state-in-a-box neural networks.

This paper is concerned with large scale associative memory design. A serious problem with neural associative memories is the quadratic growth of the number of interconnections with the problem size. An overlapping decomposition algorithm is proposed to attack this problem. Specifically, a pattern to be processed is decomposed into overlapping sub-patterns. Then, neural sub-networks are constructed that process the sub-patterns. An error correction algorithm operates on the outputs of each sub-network in order to correct the mismatches between sub-patterns that are obtained from the independent recall processes of individual sub-networks. The performance of the proposed large scale associative memory is illustrated using two-dimensional images. It is shown that the proposed method reduces the computing cost of the design of the associative memories compared with non-interconnected associative memories.

Algorithms↗

PubMed1998

Toward optimally distributed computation.

This article introduces the concept of optimally distributed computation in feedforward neural networks via regularization of weight saliency. By constraining the relative importance of the parameters, computation can be distributed thinly and evenly throughout the network. We propose that this will have beneficial effects on fault-tolerance performance and generalization ability in large network architectures. These theoretical predictions are verified by simulation experiments on two problems: one artificial and the other a real-world task. In summary, this article presents regularization terms for distributing neural computation optimally.

Computer Simulation↗

PubMedDate not supplied

Neural networks in clinical medicine.

Neural networks are parallel, distributed, adaptive information-processing systems that develop their functionality in response to exposure to information. This paper is a tutorial for researchers intending to use neural nets for medical decision-making applications. It includes detailed discussion of the issues particularly relevant to medical data as well as wider issues relevant to any neural net application. The article is restricted to back-propagation learning in multilayer perceptrons, as this is the neural net model most widely used in medical applications.

Algorithms↗

PubMed1994

Modelling symmetry detection with back-propagation networks.

This paper reports experimental data and results of network simulations in a project on symmetry detection in small 6 x 6 binary patterns. Patterns were symmetrical about the vertical, horizontal, positive-oblique, or negative-oblique axis, and were viewed on a computer screen. Encouraged to react quickly and accurately, subjects indicated axis of symmetry by pressing one of four designated keys. Detection times and errors were recorded. Back-propagation networks were trained to categorize the patterns on the basis of axis of symmetry, and, by employing cascaded activation functions on their output units, it was possible to compare network performance with subjects' detection times. Best correspondence between simulated and human detection-time functions was observed after the networks had been given significantly more training on patterns symmetrical about the vertical and the horizontal axes. In comparison with no pre-training and pre-training with asymmetric patterns, pre-training networks with sets of single vertical, horizontal, positive-oblique or negative-oblique bars speeded subsequent learning of symmetrical patterns. Results are discussed within the context of theories suggesting that faster detection of symmetries about the vertical and horizontal axes may be due to significantly more early experience with stimuli oriented on these axes.

Computer Simulation↗

PubMed2006

Systematic series expansions for processes on networks.

We use series expansions to study dynamics of equilibrium and nonequilibrium systems on networks. This analytical method enables us to include detailed nonuniversal effects of the network structure. We show that even low order calculations produce results which compare accurately to numerical simulation, while the results can be systematically improved. We show that certain commonly accepted analytical results for the critical point on networks with a broad degree distribution need to be modified in certain cases due to disassortativity; the present method is able to take into account the assortativity at sufficiently high order, while previous results correspond to leading and second order approximations in this method. Finally, we apply this method to real-world data.

Computational Biology↗

PubMed2003

Artificial neural network learning of nonstationary behavior in time series.

We refine and complement a previously-proposed artificial neural network method for learning hidden signals forcing nonstationary behavior in time series. The method adds an extra input unit to the network and feeds it with the proposed profile for the unknown perturbing signal. The correct time evolution of this new input parameter is learned simultaneously with the intrinsic stationary dynamics underlying the series, which is accomplished by minimizing a suitably-defined error function for the training process. We incorporate here the use of validation data, held out from the training set, to accurately determine the optimal value of a hyperparameter required by the method. Furthermore, we evaluate this algorithm in a controlled situation and show that it outperforms other existing methods in the literature. Finally, we discuss a preliminary application to the real-world sunspot time series and link the obtained hidden perturbing signal to the secular evolution of the solar magnetic field.

Algorithms↗

PubMed2001

Simultaneity of responses in a hierarchical visual network.

The pattern of anatomical connections between areas of the primate visual system is organized hierarchically. However, onset latencies in parietal and occipital stations are often simultaneous, and this seems to contradict hierarchical organization in its simplest interpretation, as serial organization. To understand the reasons for this contradiction, we simulated the cortical network for which there is onset data, including the network's hierarchical structure. The network's dynamics reproduced the simultaneous onset latencies reported in several dorsal areas. These results show that a strictly hierarchical visual system is compatible with much more complex dynamics than serial processing, and that hodological and biophysical properties, are more closely related to onset dynamics than is hierarchical organisation.

Animals↗

PubMed2002

Rational drug discovery: what can we learn from regulatory networks?

To enable the list of genes and proteins contained within genomic databases to be useful for drug discovery, we need to understand how the genome maps into the phenome. An essential, but not explicitly listed ingredient of the genome is the regulatory interactions between genes and proteins that form a genome-wide network. How can the concept of regulatory networks increase our understanding of living systems? Networks are more than just static "wiring diagrams". Gene interactions impose dynamic constraints, which, although obvious in emergent phenotypic properties, are not captured by traditional one gene-one trait approaches. Understanding the nature of these constraints in gene-activation state space will pave the way to a holistic yet formal and genomics-based approach to rational drug development.

Computational Biology↗

PubMed1994

Generating explanations and tutorial problems from Bayesian networks.

We present a system that generates explanations and tutorial problems from the probabilistic information contained in Bayesian belief networks. BANTER is a tool for high-level interaction with any Bayesian network whose nodes can be classified as hypotheses, observations, and diagnostic procedures. Users need no knowledge of Bayesian networks, only familiarity with the particular domain and an elementary understanding of probability. Users can query the knowledge base, identify optimal diagnostic procedures, and request explanations. We describe BANTER's algorithms and illustrate its application to an existing medical model.

Algorithms↗

PubMed2001

A hybrid learning network for shift, orientation, and scaling invariant pattern recognition.

A three-layer neural network is presented as a generic approach for visual pattern recognition invariant with respect to the geometric appearance such as translation, orientation and scale of the patterns. The invariant recognition is achieved by representing the geometric variations internally in the network by nodes in the input and middle layers, which are laterally connected and trained by a hybrid algorithm combining both competitive and Hebbian learning. As the result of the hybrid learning, each pattern will be represented by a particular subset of middle-layer nodes all specialized to respond to the same pattern but with different geometric appearances. The nodes in the output layer are then trained by competitive learning to recognize the different pattern internally represented by the middle-layer nodes, independent of their location, orientation and size. The proposed algorithm is generic and robust and can be applied to various practical recognition problems. Moreover, the network is relatively simple and biologically plausible and can serve as a computational model to account for the invariant object recognition in the biological visual system.

Algorithms↗