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 847 records · Page 47Linked to original sources

PubMed2001

Computational design and nonlinear dynamics of a recurrent network model of the primary visual cortex.

Recurrent interactions in the primary visual cortex make its output a complex nonlinear transform of its input. This transform serves preattentive visual segmentation, that is, autonomously processing visual inputs to give outputs that selectively emphasize certain features for segmentation. An analytical understanding of the nonlinear dynamics of the recurrent neural circuit is essential to harness its computational power. We derive requirements on the neural architecture, components, and connection weights of a biologically plausible model of the cortex such that region segmentation, figure-ground segregation, and contour enhancement can be achieved simultaneously. In addition, we analyze the conditions governing neural oscillations, illusory contours, and the absence of visual hallucinations. Many of our analytical techniques can be applied to other recurrent networks with translation-invariant neural and connection structures.

Animals↗

PubMed2004

Spiking Phineas Gage: a neurocomputational theory of cognitive-affective integration in decision making.

The authors present a neurological theory of how cognitive information and emotional information are integrated in the nucleus accumbens during effective decision making. They describe how the nucleus accumbens acts as a gateway to integrate cognitive information from the ventromedial prefrontal cortex and the hippocampus with emotional information from the amygdala. The authors have modeled this integration by a network of spiking artificial neurons organized into separate areas and used this computational model to simulate 2 kinds of cognitive-affective integration. The model simulates successful performance by people with normal cognitive-affective integration. The model also simulates the historical case of Phineas Gage as well as subsequent patients whose ability to make decisions became impeded by damage to the ventromedial prefrontal cortex.

Affect↗

PubMed1995

From image processing to classification: II. Classification of electrophoretic patterns using self-organizing feature maps and feed-forward neural networks.

In a recent study, isoelectric focusing patterns were classified with a neural network using the back-propagation algorithm [1]. In order to further study the classification process and to generalize the presentation of electrophoretic patterns, Kohonen's self-organizing feature maps [2] were applied in this study. Although these feature maps are very efficient in many pattern recognition tasks, our data proved to be too complex for classification with an unsupervised system. Therefore, a second supervised network on top of the feature map was necessary. As in [3], a feed-forward network trained by the back-propagation algorithm was used. The final system allows us to correctly classify 90% of all wheat varieties. Moreover, the system proved to be reliable, reasonable in training time and shows the same accuracy in different experimental setups.

Algorithms↗

PubMed2005

A network model for blind source extraction in various ill-conditioned cases.

This paper discusses blind source extraction in various ill-conditioned cases based on a simple extraction network model. Extractability is first analyzed for the following ill-conditioned cases: the mixing matrix is square but singular, the number of sensors is smaller than that of sources, the number of sensors is larger than that of sources but the column rank of mixing matrix is deficient, and the number of sources is unknown and the column rank of mixing matrix is deficient. A necessary and sufficient condition for extractability is obtained. A cost function and an unsupervised learning algorithm for the extraction network model are developed. Simulation results are also presented to show the validity of the theoretical results and the performance and characteristics of the learning algorithm.

Algorithms↗

PubMed2006

Prediction of liquid chromatographic retention times of peptides generated by protease digestion of the Escherichia coli proteome using artificial neural networks.

We developed a computational method to predict the retention times of peptides in HPLC using artificial neural networks (ANN). We performed stepwise multiple linear regressions and selected for ANN input amino acids that significantly affected the LC retention time. Unlike conventional linear models, the trained ANN accurately predicted the retention time of peptides containing up to 50 amino acid residues. In 834 peptides, there was a strong correlation (R2 = 0.928) between measured and predicted retention times. We demonstrated the utility of our method by the prediction of the retention time of 121,273 peptides resulting from LysC-digestion of the Escherichia coli proteome. Our approach is useful for the proteome-wide characterization of peptides and the identification of unknown peptide peaks obtained in proteome analysis.

Chromatography, High Pressure Liquid↗

PubMed1995

Compensatory mechanisms in an attractor neural network model of schizophrenia.

We investigate the effect of synaptic compensation on the dynamic behavior of an attractor neural network receiving its input stimuli as external fields projecting on the network. It is shown how, in the face of weakened inputs, memory performance may be preserved by strengthening internal synaptic connections and increasing the noise level. Yet, these compensatory changes necessarily have adverse side effects, leading to spontaneous, stimulus-independent retrieval of stored patterns. These results can support Stevens' recent hypothesis that the onset of schizophrenia is associated with frontal synaptic regeneration, occurring subsequent to the degeneration of temporal neurons projecting on these areas.

Brain↗

PubMed2004

Size invariance does not hold for connectionist models: dangers of using a toy model.

Connectionist models with backpropagation learning rule are known to have a serious problem called catastrophic interference or forgetting, although there have been several reports showing that the interference can be relatively mild with orthogonal inputs. The present study investigated the extent of interference using orthogonal inputs with varying network sizes. One would naturally assume that results obtained from small networks could be extrapolated for larger networks. Unexpectedly, the use of small networks was shown to worsen performance. This result has important implications for interpreting some data in the literature and cautions against the use of a toy model.

Algorithms↗

PubMed1993

A theory of dopamine function and its role in cognitive deficits in schizophrenia.

In spite of extensive research on the biological and behavioral correlates of dopamine (DA) function, little is known about the mechanisms by which DA may produce the cognitive deficits observed in schizophrenia. Neural network simulation models offer a framework for exploring how DA effects at the physiological level may influence behavior. We focus on findings suggesting that DA modulates neuronal activity by enhancing the ability of neurons to transmit signals and reduce distortion by noise. These phenomena can be captured in simulations by increasing the gain of individual units of a network. When gain is increased diffusely, improvement in signal detection performance of such a network parallels the improvement in performance of human subjects receiving DA agonists. Furthermore, decreasing gain in a network module supporting a memory function analogous to that of prefrontal cortex results in deterioration of performance equivalent to that of schizophrenic subjects. A test of predictions made by such networks about the performance of schizophrenic patients in a new variant of the Continuous Performance Test is discussed. Preliminary data are consistent with predictions and support the account of schizophrenic cognitive deficits in terms of the theory of DA function suggested by the models.

Antipsychotic Agents↗

PubMed2001

Artificial neural networks for blur identification and restoration of nonlinearly degraded images.

In this paper, an image restoration algorithm is proposed to identify noncausal blur function. Image degradation processes include both linear and nonlinear phenomena. A neural network model combining an adaptive auto-associative network with a random Gaussian process is proposed to restore the blurred image and blur function simultaneously. The noisy and blurred images are modeled as continuous associative networks, whereas auto-associative part determines the image model coefficients and the hetero-associative part determines the blur function of the system. The self-organization like structure provides the potential solution of the blind image restoration problem. The estimation and restoration are implemented by using an iterative gradient based algorithm to minimize the error function.

Algorithms↗

PubMed1996

Nonlinearities within the cat LGN cell receptive fields in simulated network with recurrent inhibition.

We investigated the receptive fields of principal cells from the cat's lateral geniculate nucleus cells. About 20% of the X type neurones showed clear nonlinearities of summation when stimulated by two simultaneously onset, small bars of light. The possible source of this nonlinearity was studied on a specially designed model of a one-layer neuronal network with inhibitory, recurrent interactions, intended to mimic the inhibitory influence exerted on geniculate relay cells by perigeniculate interneurones. The model, when activated from periphery by two stimuli-like input patterns, produced at the output side the nonsymmetrical profiles of the receptive fields sensitivity, similar to those obtained in real experiments. This nonlinear output appeared when some of the relay cells were inhibited below their firing level threshold and this effect was spread through the network by lateral inhibitory connections. It is concluded that physiologically observed nonlinearities of the order of single receptive field mechanisms can be predicted by a simple recurrent network.

Animals↗

PubMed2006

A comprehensive overview of the applications of artificial life.

We review the applications of artificial life (ALife), the creation of synthetic life on computers to study, simulate, and understand living systems. The definition and features of ALife are shown by application studies. ALife application fields treated include robot control, robot manufacturing, practical robots, computer graphics, natural phenomenon modeling, entertainment, games, music, economics, Internet, information processing, industrial design, simulation software, electronics, security, data mining, and telecommunications. In order to show the status of ALife application research, this review primarily features a survey of about 180 ALife application articles rather than a selected representation of a few articles. Evolutionary computation is the most popular method for designing such applications, but recently swarm intelligence, artificial immune network, and agent-based modeling have also produced results. Applications were initially restricted to the robotics and computer graphics, but presently, many different applications in engineering areas are of interest.

Artificial Intelligence↗

PubMed1994

Neural network analysis of flow cytometric data for 40 marine phytoplankton species.

Flow cytometry data (time of flight, horizontal and vertical forward light scatter, 90 degrees light scatter, and "red" and "orange" integral fluorescence) were collected for laboratory cultures of 40 species of marine phytoplankton, from the following taxonomic classes, the Dinophyceae, Bacillariophyceae, Prymnesiophyceae, Cryptophyceae, and other flagellates. Single-hidden-layer "back-propagation" neural networks were trained to discriminate between species by recognising patterns in their flow cytometric signatures, and network performance was assessed using an independent test data set. Two approaches were adopted employing: (1) a hierarchy of small networks, the first identifying to which major taxonomic group a cell belonged, and then a network for that taxonomic group identified to species, and (2) a single large network. Discriminating some of the major taxonomic groups was successful but others less so. With networks for specific groups, cryptophyte species were all identified reliably (probability of correct classification always being > 0.75); in the other groups half of the species were identified reliably. With the large network, dinoflagellates, cryptomonads, and flagellates were identified almost as well as by networks specific for these groups. The application of neural computing techniques to identification of such a large number of species represents a significant advance from earlier studies, although further development is required.

Flow Cytometry↗

PubMed1994

NNERVE: neural network extraction of repetitive vectors for electromyography--Part I: Algorithm.

Artificial neural network (ANN) based signal processing methods have been shown to have significant robustness in processing complex, degraded, noisy, and unstable signals. A novel approach to automated electromyogram (EMG) signal decomposition, using an ANN processing architecture, is presented in this paper. Due to the lack of a priori knowledge of motor unit action potential (MUAP) morphology, the EMG decomposition must be performed in an unsupervised manner. An ANN classifier, consisting of a multilayer perceptron neural network and employing a novel unsupervised training strategy, is proposed. The ANN learns repetitive appearances of MUAP waveforms from their suspected occurrences in a filtered EMG signal in an autoassociative learning task. The same training waveforms are fed into the trained ANN and the output of the ANN is fed back to its input, giving rise to a dynamic retrieval net classifier. For each waveform in the data, the network discovers a feature vector associated with that waveform. For each waveform, classification is achieved by comparing its feature vector with those of the other waveforms. Firing information of each MUAP is further used to refine the classification results of the ANN classifier. Then, individual MUAP waveform shapes are derived and their firing tables are created.

Algorithms↗

PubMed2006

Dynamics analysis and analog associative memory of networks with LT neurons.

The additive recurrent network structure of linear threshold neurons represents a class of biologically-motivated models, where nonsaturating transfer functions are necessary for representing neuronal activities, such as that of cortical neurons. This paper extends the existing results of dynamics analysis of such linear threshold networks by establishing new and milder conditions for boundedness and asymptotical stability, while allowing for multistability. As a condition for asymptotical stability, it is found that boundedness does not require a deterministic matrix to be symmetric or possess positive off-diagonal entries. The conditions put forward an explicit way to design and analyze such networks. Based on the established theory, an alternate approach to study such networks is through permitted and forbidden sets. An application of the linear threshold (LT) network is analog associative memory, for which a simple design method describing the associative memory is suggested in this paper. The proposed design method is similar to a generalized Hebbian approach, but with distinctions of additional network parameters for normalization, excitation and inhibition, both on a global and local scale. The computational abilities of the network are dependent on its nonlinear dynamics, which in turn is reliant upon the sparsity of the memory vectors.

Algorithms↗

PubMed2006

The role of short-term depression in sustained neural activity in the prefrontal cortex: a simulation study.

Recent experimental researches have suggested that sustained neural activity in the prefrontal cortex is a process of memory retention in decision making. Previous theoretical studies indicate that a balance between recurrent excitation and feedback inhibition is important for sustaining the activity. To investigate a plausible balancing mechanism, we simulated a biophysically realistic network model. Our model shows that short-term depression (STD) enables the network to sustain its activity despite the presence of long-term inhibition by GABA(B) receptors and that the sustained firing rates have a bell-shaped dependence on the degree of STD. By analyzing the neural network dynamics, we show that the bell-shaped dependence on STD is formed by destabilizing the balance with either excessive or insufficient STD. We also show that the optimal degree of STD has a linear relationship with the neural network size. These results suggest that STD provides a balancing mechanism and controls levels of sustained activities of various size networks.

Action Potentials↗

PubMed2005

Comments on "The multisynapse neural network and its application to fuzzy clustering".

In the above-mentioned paper, Wei and Fahn proposed a neural architecture, the multisynapse neural network, to solve constrained optimization problems including high-order, logarithmic, and sinusoidal forms, etc. As one of its main applications, a fuzzy bidirectional associative clustering network (FBACN) was proposed for fuzzy-partition clustering according to the objective-functional method. The connection between the objective-functional-based fuzzy c-partition algorithms and FBACN is the Lagrange multiplier approach. Unfortunately, the Lagrange multiplier approach was incorrectly applied so that FBACN does not equivalently minimize its corresponding constrained objective-function. Additionally, Wei and Fahn adopted traditional definition of fuzzy c-partition, which is not satisfied by FBACN. Therefore, FBACN can not solve constrained optimization problems, either.

Algorithms↗

PubMed2002

Modeling of nonlinear physiological systems with fast and slow dynamics. I. Methodology.

Effective modeling of nonlinear dynamic systems can be achieved by employing Laguerre expansions and feedforward artificial neural networks in the form of the Laguerre-Volterra network (LVN). This paper presents a different formulation of the LVN that can be employed to model nonlinear systems displaying complex dynamics effectively. This is achieved by using two different filter banks, instead of one as in the original definition of the LVN, in the input stage and selecting their structural parameters in an appropriate way. Results from simulated systems show that this method can yield accurate nonlinear models of Volterra systems, even when considerable noise is present, separating at the same time the fast from the slow components of these systems effectively.

Algorithms↗

PubMed1996

Stable encoding of large finite-state automata in recurrent neural networks with sigmoid discriminants.

We propose an algorithm for encoding deterministic finite-state automata (DFAs) in second-order recurrent neural networks with sigmoidal discriminant function and we prove that the languages accepted by the constructed network and the DFA are identical. The desired finite-state network dynamics is achieved by programming a small subset of all weights. A worst case analysis reveals a relationship between the weight strength and the maximum allowed network size, which guarantees finite-state behavior of the constructed network. We illustrate the method by encoding random DFAs with 10, 100, and 1000 states. While the theory predicts that the weight strength scales with the DFA size, we find empirically the weight strength to be almost constant for all the random DFAs. These results can be explained by noting that the generated DFAs represent average cases. We empirically demonstrate the existence of extreme DFAs for which the weight strength scales with DFA size.

Algorithms↗