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 1,441 records · Page 80Linked to original sources
PubMed2004

Information coding and oscillatory activity in synfire neural networks with and without inhibitory coupling.

When a population spike (pulse-packet) propagates through a feedforward network with random excitatory connections, it either evolves to a sustained stable level of synchronous activity or fades away (Diesmann et al. in Nature 402:529-533 1999; Cateau and Fukai Neur Netw 14:675-685 2001). Here I demonstrate that in the presence of noise, the probability of the survival of the pulse-packet (or, equivalently, the firing rate of output neurons) reflects the intensity of the input. Furthermore, inhibitory coupling between layers can result in quasi- periodic alternation between several levels of firing activity. These results are obtained by analyzing the evolution of pulse-packet activity as a Markov chain. For the Markov chain analysis, the output of the chain is a linear mapping of the input into a lower-dimensional space, and the eigenvalues and eigenvectors of the transition matrix determine the dynamics of the evolution. Synchronous propagation of firing activity in successive pools of neurons are simulated in networks of integrate-and-fire and compartmental model neurons, and, consistent with the discrete Markov process, the activation of each pool is observed to be predominantly dependent upon the number of cells that fired in the previous pool. Simulation results agree with the numerical solutions of the Markov model. When inhibitory coupling between layers are included in the Markov model, some eigenvalues become complex numbers, implying oscillatory dynamics. The quasiperiodic dynamics is validated with simulation with leaky integrate-and-fire neurons. The networks demonstrate different modes of quasiperiodic activity as the inhibition or excitation parameters of the network are varied.

Action Potentials↗
PubMed2003

YADCLAN: yet another digitally-controlled linear artificial neuron.

This paper updates the author's 1999 RMBS presentation on digitally controlled linear artificial neuron design. Each neuron is based on a standard operational amplifier having excitatory and inhibitory inputs, variable gain, an amplified linear analog output and an adjustable threshold comparator for digital output. This design employs a 1-wire serial network of digitally controlled potentiometers and resistors whose resistance values are set and read back under microprocessor supervision. This system embodies several unique and useful features, including: enhanced neuronal stability, dynamic reconfigurability and network extensibility. This artificial neuronal is being employed for feature extraction and pattern recognition in an advanced robotic application.

Amplifiers, Electronic↗
PubMed1993

The dynamics of sparse random networks.

Recurrent neural networks with full symmetric connectivity have been extensively studied as associative memories and pattern recognition devices. However, there is considerable evidence that sparse, asymmetrically connected, mainly excitatory networks with broadly directed inhibition are more consistent with biological reality. In this paper, we use the technique of return maps to study the dynamics of random networks with sparse, asymmetric connectivity and nonspecific inhibition. These networks show three qualitatively different kinds of behavior: fixed points, cycles of low period, and extremely long cycles verging on aperiodicity. Using statistical arguments, we relate these behaviors to network parameters and present empirical evidence for the accuracy of this statistical model. The model, in turn, leads to methods for controlling the level of activity in networks. Studying random, untrained networks provides an understanding of the intrinsic dynamics of these systems. Such dynamics could provide a substrate for the much more complex behavior shown when synaptic modification is allowed.

Animals↗
PubMed2004

Spiking neural network for recognizing spatiotemporal sequences of spikes.

Sensory neurons in many brain areas spike with precise timing to stimuli with temporal structures, and encode temporally complex stimuli into spatiotemporal spikes. How the downstream neurons read out such neural code is an important unsolved problem. In this paper, we describe a decoding scheme using a spiking recurrent neural network. The network consists of excitatory neurons that form a synfire chain, and two globally inhibitory interneurons of different types that provide delayed feedforward and fast feedback inhibition, respectively. The network signals recognition of a specific spatiotemporal sequence when the last excitatory neuron down the synfire chain spikes, which happens if and only if that sequence was present in the input spike stream. The recognition scheme is invariant to variations in the intervals between input spikes within some range. The computation of the network can be mapped into that of a finite state machine. Our network provides a simple way to decode spatiotemporal spikes with diverse types of neurons.

Action Potentials↗
PubMed2005

The loading problem for recursive neural networks.

The present work deals with one of the major and not yet completely understood topics of supervised connectionist models. Namely, it investigates the relationships between the difficulty of a given learning task and the chosen neural network architecture. These relationships have been investigated and nicely established for some interesting problems in the case of neural networks used for processing vectors and sequences, but only a few studies have dealt with loading problems involving graphical inputs. In this paper, we present sufficient conditions which guarantee the absence of local minima of the error function in the case of learning directed acyclic graphs with recursive neural networks. We introduce topological indices which can be directly calculated from the given training set and that allows us to design the neural architecture with local minima free error function. In particular, we conceive a reduction algorithm that involves both the information attached to the nodes and the topology, which enlarges significantly the class of the problems with unimodal error function previously proposed in the literature.

Algorithms↗
PubMed2006

The added value of ECG-gating for the diagnosis of myocardial infarction using myocardial perfusion scintigraphy and artificial neural networks.

To assess the value of ECG-gating for the diagnosis of myocardial infarction using myocardial perfusion scintigraphy (MPS) and an artificial neural network. A total of 422 patients referred for MPS were studied using a one day (99m)Tc-tetrofosmin protocol. Adenosine stress combined with submaximal dynamic exercise was used. The images were interpreted by one of three experienced clinicians and these interpretations regarding the presence or absence of myocardial infarction were used as the standard. A fully automated method using artificial neural networks was compared with the clinical interpretation. Either perfusion data alone or a combination of perfusion and function from ECG-gated images were used as input to different artificial neural networks. After a training session, the two types of neural networks were evaluated in separate test groups using an eightfold cross-validation procedure. The neural networks trained with both perfusion and ECG-gated images had a 4-7% higher specificity compared with the corresponding networks using perfusion data only, in four of five segments compared at the same level of sensitivity. The greatest improvement in specificity, from 70% to 77%, was seen in the inferior segment. In the septal and lateral segments the specificity rose from 73% to 77% and from 81% to 85%, respectively. In the anterior segment, the increase in specificity from 93% to 94% by adding functional data was not significant. The addition of functional information from ECG-gated MPS is of value for the diagnosis of myocardial infarction using an automated method of interpreting myocardial perfusion images.

Adenosine↗
PubMed2000

Mode dynamics of interacting neural populations by bi-orthogonal spectral decomposition.

A system of coupled bistable Hopf oscillators with an external periodic input source was used to model the ability of interacting neural populations to synchronize and desynchronize in response to variations of the input signal. We propose that, in biological systems, the settings of internal and external coupling strengths will affect the behaviour of the system to a greater degree than the input frequency. While input frequency and coupling strength were varied, the spatio-temporal dynamics of the network was examined by the bi-orthogonal decomposition technique. Within this method, effects of variation of input frequency and coupling strength were analyzed in terms of global, spatial and temporal mode entropy and energy, using the spatio-temporal data of the system. We observed a discontinuous evolution of spatio-temporal patterns depending sensitively on both the input frequency and the internal and external coupling strengths of the network.

Animals↗
PubMed2006

Cardiac state diagnosis using adaptive neuro-fuzzy technique.

Analysis of heart rate has become a popular noninvasive tool for assessing the activities of the autonomic nervous system (ANS). These signals may either contain indicators of a current disease or even warnings about impending diseases. However, to manually study and pinpoint heart abnormalities in voluminous data is strenuous and time consuming. Here, an adaptive neuro-fuzzy network is used to classify heart abnormalities in 10 different cardiac states and shown to be effective. The results indicate a high level of efficacy of tools used with an accuracy level of more than 94%.

Algorithms↗
PubMed1999

Fast global oscillations in networks of integrate-and-fire neurons with low firing rates.

We study analytically the dynamics of a network of sparsely connected inhibitory integrate-and-fire neurons in a regime where individual neurons emit spikes irregularly and at a low rate. In the limit when the number of neurons --> infinity, the network exhibits a sharp transition between a stationary and an oscillatory global activity regime where neurons are weakly synchronized. The activity becomes oscillatory when the inhibitory feedback is strong enough. The period of the global oscillation is found to be mainly controlled by synaptic times but depends also on the characteristics of the external input. In large but finite networks, the analysis shows that global oscillations of finite coherence time generically exist both above and below the critical inhibition threshold. Their characteristics are determined as functions of systems parameters in these two different regions. The results are found to be in good agreement with numerical simulations.

Algorithms↗
PubMed1992

Computer-assisted image interpretation: use of a neural network to differentiate tubular carcinoma from sclerosing adenosis.

Measurement of nuclear and glandular size and shape features was carried out on 18 cases of sclerosing adenosis and 18 cases of tubular carcinoma. Modified Bonferroni analysis showed that glandular surface density and the coefficient of variation of luminal form factor were significant in discriminating between these two lesions. These two histologic features, together with the diagnosis, were used to train a neural network implementing a backpropagation algorithm. Following training, the network correctly classified 33 of the 36 cases in the training set (92%). Furthermore, the network correctly classified 19 of 19 cases in a test set consisting of cases that were not used to train the network. These results suggest that neural networks may be useful to assist in the differential diagnosis of histologically similar lesions.

Adenocarcinoma↗
PubMed2004

Unsupervised fuzzy clustering using Weighted Incremental Neural Networks.

A new more efficient variant of a recently developed algorithm for unsupervised fuzzy clustering is introduced. A Weighted Incremental Neural Network (WINN) is introduced and used for this purpose. The new approach is called FC-WINN (Fuzzy Clustering using WINN). The WINN algorithm produces a net of nodes connected by edges, which reflects and preserves the topology of the input data set. Additional weights, which are proportional to the local densities in input space, are associated with the resulting nodes and edges to store useful information about the topological relations in the given input data set. A fuzziness factor, proportional to the connectedness of the net, is introduced in the system. A watershed-like procedure is used to cluster the resulting net. The number of the resulting clusters is determined by this procedure. Only two parameters must be chosen by the user for the FC-WINN algorithm to determine the resolution and the connectedness of the net. Other parameters that must be specified are those which are necessary for the used incremental neural network, which is a modified version of the Growing Neural Gas algorithm (GNG). The FC-WINN algorithm is computationally efficient when compared to other approaches for clustering large high-dimensional data sets.

Algorithms↗
PubMed2004

Epilepsy in small-world networks.

In hippocampal slice models of epilepsy, two behaviors are seen: short bursts of electrical activity lasting 100 msec and seizure-like electrical activity lasting seconds. The bursts originate from the CA3 region, where there is a high degree of recurrent excitatory connections. Seizures originate from the CA1, where there are fewer recurrent connections. In attempting to explain this behavior, we simulated model networks of excitatory neurons using several types of model neurons. The model neurons were connected in a ring containing predominantly local connections and some long-distance random connections, resulting in a small-world network connectivity pattern. By changing parameters such as the synaptic strengths, number of synapses per neuron, proportion of local versus long-distance connections, we induced "normal," "seizing," and "bursting" behaviors. Based on these simulations, we made a simple mathematical description of these networks under well-defined assumptions. This mathematical description explains how specific changes in the topology or synaptic strength in the model cause transitions from normal to seizing and then to bursting. These behaviors appear to be general properties of excitatory networks.

Cell Communication↗
PubMed2003

Application of filter technology in photomorphogenesis gene network.

Light regulates almost all physiological and biochemical processes in plants. Plants react to quantitative and qualitative light characteristics owing to the system of photoreceptors and a branched network for light signal transduction. Comprehensible visual representations of gene networks using of filter technology in the GeneNet system assist understanding the types of the relationships between the components inside the networks and to define their hierarchical structure.

Computational Biology↗
PubMed2006

Computer inference of network of ecological interactions from sampling data.

Both direct and indirect ecological interactions may occur in an ecosystem with large numbers of taxa. Traditional food web technique is a popular tool to measure the quality and health of the environment. Much of works must be done before constructing a food web for an ecosystem especially with many taxa. This food web is generally specific for some ecological interactions and fixed for a set of given species. It is therefore not an effective method for dynamic and prompt assessment of environment. Ecological interactions and their interactive intensity may be detected by sampling biological taxa in the field and by detecting various between-taxa distances or similarities. Network may clearly exhibit the complex interactions among biological taxa. Statistic tests on various distance or similarity measures and computer designs are required to infer the {network. We develop an algorithm and software to infer the network of direct or indirect ecological interactions in ecosystem. It is a prompt and effective tool in monitoring and assessment of the environment. A redundant network may be inferred and drawn by computer based on the statistic tests on sampling data or the pathway information given in HTML file. Dominant taxa may be found in the network. In total of 16 distance and similarity measures, including Euclidean distance, Manhattan distance, Pearson correlation, partial correlation, point correlation, linkage coefficients, Jaccard coefficient etc., are provided to detect taxa pairs with significant parametric or nonparametric similarities, based on randomization tests and ordinary statistic tests. Criteria to use distance and similarity measures are discussed.

Algorithms↗
PubMed1993

Neural network segmentation of magnetic resonance spin echo images of the brain.

This paper describes a neural network system to segment magnetic resonance (MR) spin echo images of the brain. Our approach relies on the analysis of MR signal decay and on anatomical knowledge; the system processes two early echoes of a standard multislice sequence. Three main subsystems can be distinguished. The first implements a model of MR signal decay; it synthesizes a four-echo multiecho sequence, in order to add images characterized by long echo-times to the input sequence. The second subsystem exploits a priori anatomical knowledge by producing an image, in which pixels belonging to brain parenchyma are highlighted. Such anatomical information allows the following submodule to distinguish biologically different tissues with similar water content, and hence similar appearance, which might produce misclassifications. The grey levels of the reconstructed sequence and the output of the second module are processed by the third subsystem, which performs the segmentation of the sequence. Each pixel is assigned to one of five different tissue classes that can be revealed with brain MR spin echo imaging. With a suitable encoding, a five-level segmented image can then be produced. The system is based on feed-forward networks trained with the back-propagation algorithm; experiments to assess its performance have been carried out on both simulated and clinical images.

Brain↗
PubMed1991

Using neural networks to diagnose cancer.

While artificial brains are in the realm of science fiction, artificial neural networks (ANNs) are scientific facts. An artificial neural network is a computational structure modeled somewhat on the neural structure of the brain; both have many highly interconnected processing elements. These biologically inspired processing elements are taught by feeding examples until the results are acceptable. In the past 5 years, neural networks have become successful in providing meaningful second opinions in clinical diagnosis. In our research, a prototype artificial neural network was trained on numeral ultrasound data of 52 actual cases and then correctly identified renal cell carcinoma from renal cysts and other conditions without diagnostic errors. Our nonlinear artificial neural network was trained on software using the standard backpropagation paradigm on a 80386 microcomputer. Our ANN learned from ultrasound data in 52 cases (17 malignant, 30 cysts, and 5 other) at a Memphis hospital. The trained prototype performed without error on 47 cases which were not in the data used for training. This prototype must be validated by extending this study to more cases.

Carcinoma, Renal Cell↗
PubMed2003

Electrical synapses and synchrony: the role of intrinsic currents.

Electrical synapses are ubiquitous in the mammalian CNS. Particularly in the neocortex, electrical synapses have been shown to connect low-threshold spiking (LTS) as well as fast spiking (FS) interneurons. Experiments have highlighted the roles of electrical synapses in the dynamics of neuronal networks. Here we investigate theoretically how intrinsic cell properties affect the synchronization of neurons interacting by electrical synapses. Numerical simulations of a network of conductance-based neurons randomly connected with electrical synapses show that potassium currents promote synchrony, whereas the persistent sodium current impedes it. Furthermore, synchrony varies with the firing rate in qualitatively different ways depending on the intrinsic currents. We also study analytically a network of quadratic integrate-and-fire neurons. We relate the stability of the asynchronous state of this network to the phase-response function (PRF), which characterizes the effect of small perturbations on the firing timing of the neurons. In particular, we show that the greater the skew of the PRF toward the first half of the period, the more stable the asynchronous state. Combining our simulations with our analytical results, we establish general rules to predict the dynamic state of large networks of neurons coupled with electrical synapses. Our work provides a natural explanation for surprising experimental observations that blocking electrical synapses may increase the synchrony of neuronal activity. It also suggests different synchronization properties for LTS and FS cells. Finally, we propose to further test our predictions in experiments using dynamic clamp techniques.

Computer Simulation↗