Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Neural network”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 775 records · Page 43Linked to original sources
PubMed2003

A hybrid neural network of addressable and content-addressable memory.

We investigate the memory structure and retrieval of the brain and propose a hybrid neural network of addressable and content-addressable memory which is a special database model and can memorize and retrieve any piece of information (a binary pattern) both addressably and content-addressably. The architecture of this hybrid neural network is hierarchical and takes the form of a tree of slabs which consist of binary neurons with the same array. Simplex memory neural networks are considered as the slabs of basic memory units, being distributed on the terminal vertexes of the tree. It is shown by theoretical analysis that the hybrid neural network is able to be constructed with Hebbian and competitive learning rules, and some other important characteristics of its learning and memory behavior are also consistent with those of the brain. Moreover, we demonstrate the hybrid neural network on a set of ten binary numeral patters

Artificial Intelligence↗
PubMed1998

Unsupervised classification of neural spikes with a hybrid multilayer artificial neural network.

The understanding of the brain structure and function and its computational style is one of the biggest challenges both in Neuroscience and Neural Computation. In order to reach this and to test the predictions of neural network modeling, it is necessary to observe the activity of neural populations. In this paper we propose a hybrid modular computational system for the spike classification of multiunits recordings. It works with no knowledge about the waveform, and it consists of two moduli: a Preprocessing (Segmentation) module, which performs the detection and centering of spike vectors using programmed computation; and a Processing (Classification) module, which implements the general approach of neural classification: feature extraction, clustering and discrimination, by means of a hybrid unsupervised multilayer artificial neural network (HUMANN). The operations of this artificial neural network on the spike vectors are: (i) compression with a Sanger Layer from 70 points vector to five principal component vector; (ii) their waveform is analyzed by a Kohonen layer; (iii) the electrical noise and overlapping spikes are rejected by a previously unreported artificial neural network named Tolerance layer; and (iv) finally the spikes are labeled into spike classes by a Labeling layer. Each layer of the system has a specific unsupervised learning rule that progressively modifies itself until the performance of the layer has been automatically optimized. The procedure showed a high sensitivity and specificity also when working with signals containing four spike types.

Animals↗
PubMed1992

Review of neural network applications in medical imaging and signal processing.

The current applications of neural networks to in vivo medical imaging and signal processing are reviewed. As is evident from the literature neural networks have already been used for a wide variety of tasks within medicine. As this trend is expected to continue this review contains a description of recent studies to provide an appreciation of the problems associated with implementing neural networks for medical imaging and signal processing.

Diagnostic Imaging↗
PubMed1999

Gait control system for functional electrical stimulation using neural networks.

In functional electrical stimulation (FES) systems for restoring walking in spinal cord injured (SCI) individuals, hand switches are the preferred method for controlling stimulation timing. Through practice the user becomes an 'expert' in determining when stimulation should be applied. Neural networks have been used to 'clone' this expertise but these applications have used small numbers of sensors, and their structure has used a binary output, giving rise to possible controller oscillations. It was proposed that a three-layer structure neural network with continuous function, using a larger number of sensors, including 'virtual' sensors, can be used to 'clone' this expertise to produce good controllers. Using a sensor set of ten force sensors and another of 13 'virtual' kinematic sensors, a good FES control system was constructed using a three-layer neural network with five hidden nodes. The sensor set comprising three sensors showed the best performance. The accuracy of the optimum three-sensor set for the force sensors and the virtual kinematic sensors was 90% and 93%, respectively, compared with 81% and 77% for a heel switch. With 32 synchronised sensors, binary neural networks and continuous neural networks were constructed and compared. The networks using continuous function had significantly fewer oscillations. Continuous neural networks offer the ability to generate good FES controllers.

Electric Stimulation↗
PubMed2001

Neural network models of schizophrenia.

There is considerable neurobiological evidence suggesting that schizophrenia is associated with reduced corticocortical connectivity. The authors describe two neural network computer simulations that explore functional consequences of these abnormalities. The first utilized an "attractor" neural network capable of content-addressable memory. Application of a pruning rule that eliminated weaker connections over longer distances produced functional fragmentation and the emergence of localized, "parasitic" attractors that intruded into network dynamics. These pathologies generally were expressed only when input information was ambiguous and provide models for delusions and cognitive disorganization. A second neural network simulation examined effects of corticocortical pruning in a speech perception network. Excessive pruning caused the network to produce percepts spontaneously, that is, in the absence of inputs, thereby simulating hallucinations. The "hallucinating" network also demonstrated subtle impairments in narrative speech perception. A parallel study of human patients found similar impairments when comparing hallucinating patients with nonhallucinating patients. In addition, the authors have used transcranial magnetic stimulation (TMS) to directly probe speech perception neurocircuitry in patients with these hallucinations. As predicted by the neural network model, the authors confirmed that "suppressive" low-frequency TMS reduces auditory hallucinations. Neural network simulations provide empirically testable concepts linking phenomenological, cognitive, and neurobiological findings in schizophrenia.

Brain↗
PubMed1995

Development of a nursing diagnosis system using a back-propagation neural network model: an application for stomach cancer patients.

Neural networks have recently attracted considerable attention in the field of classification and in other areas. This paper discusses an experiment using a back-propagation neural network model applied to nursing diagnosis. The network's structure has three layers: 1) an input layer for representing signs and symptoms, 2) an output layer for nursing diagnosis, 3) a hidden layer. A first prototype of a nursing diagnosis system for stomach cancer patients was developed with 87 nodes for the input layer and 5 nodes for the output layer of 23 nursing diagnoses. It turned out that a model that learned 10,000 times as fast and had 5 nodes of hidden layers, a 0.5 momentum, and a 0.5 learning coefficient is the optimal one with a hitting ratio 0.76.

Computer Simulation↗
PubMed2000

Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research.

Artificial neural networks (ANNs) are biologically inspired computer programs designed to simulate the way in which the human brain processes information. ANNs gather their knowledge by detecting the patterns and relationships in data and learn (or are trained) through experience, not from programming. An ANN is formed from hundreds of single units, artificial neurons or processing elements (PE), connected with coefficients (weights), which constitute the neural structure and are organised in layers. The power of neural computations comes from connecting neurons in a network. Each PE has weighted inputs, transfer function and one output. The behavior of a neural network is determined by the transfer functions of its neurons, by the learning rule, and by the architecture itself. The weights are the adjustable parameters and, in that sense, a neural network is a parameterized system. The weighed sum of the inputs constitutes the activation of the neuron. The activation signal is passed through transfer function to produce a single output of the neuron. Transfer function introduces non-linearity to the network. During training, the inter-unit connections are optimized until the error in predictions is minimized and the network reaches the specified level of accuracy. Once the network is trained and tested it can be given new input information to predict the output. Many types of neural networks have been designed already and new ones are invented every week but all can be described by the transfer functions of their neurons, by the learning rule, and by the connection formula. ANN represents a promising modeling technique, especially for data sets having non-linear relationships which are frequently encountered in pharmaceutical processes. In terms of model specification, artificial neural networks require no knowledge of the data source but, since they often contain many weights that must be estimated, they require large training sets. In addition, ANNs can combine and incorporate both literature-based and experimental data to solve problems. The various applications of ANNs can be summarised into classification or pattern recognition, prediction and modeling. Supervised 'associating networks can be applied in pharmaceutical fields as an alternative to conventional response surface methodology. Unsupervised feature-extracting networks represent an alternative to principal component analysis. Non-adaptive unsupervised networks are able to reconstruct their patterns when presented with noisy samples and can be used for image recognition. The potential applications of ANN methodology in the pharmaceutical sciences range from interpretation of analytical data, drug and dosage form design through biopharmacy to clinical pharmacy.

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

On the misuses of artificial neural networks for prognostic and diagnostic classification in oncology.

The application of artificial neural networks (ANNs) for prognostic and diagnostic classification in clinical medicine has become very popular. In particular, feed-forward neural networks have been used extensively, often accompanied by exaggerated statements of their potential. In this paper, the essentials of feed-forward neural networks and their statistical counterparts (that is, logistic regression models) are reviewed. We point out that the uncritical use of ANNs may lead to serious problems, such as the fitting of implausible functions to describe the probability of class membership and the underestimation of misclassification probabilities. In applications of ANNs to survival data, further difficulties arise. Finally, the results of a search in the medical literature from 1991 to 1995 on applications of ANNs in oncology and some important common mistakes are reported. It is concluded that there is no evidence so far that application of ANNs represents real progress in the field of diagnosis and prognosis in oncology.

Decision Support Techniques↗
PubMed1991

A more biologically plausible learning rule for neural networks.

Many recent studies have used artificial neural network algorithms to model how the brain might process information. However, back-propagation learning, the method that is generally used to train these networks, is distinctly "unbiological." We describe here a more biologically plausible learning rule, using reinforcement learning, which we have applied to the problem of how area 7a in the posterior parietal cortex of monkeys might represent visual space in head-centered coordinates. The network behaves similarly to networks trained by using back-propagation and to neurons recorded in area 7a. These results show that a neural network does not require back propagation to acquire biologically interesting properties.

Animals↗
PubMed1992

The application of backpropagation neural networks to problems in pathology and laboratory medicine.

Neural networks are a group of computer-based pattern recognition technologies that have been applied to problems in clinical diagnosis. This review focuses on one member of the group of neural networks, the backpropagation network. The steps in creating a backpropagation network are (1) collecting adequate training facts, (2) choosing the specific network structure, (3) training the network, and (4) cross-validating the trained network. The first published applications of backpropagation networks to problems in pathology and laboratory medicine have appeared recently. These applications are in the areas of image analysis and interpretation of laboratory results, and they demonstrate the feasibility of the approach.

Evaluation Studies as Topic↗
PubMed1994

On using feedforward neural networks for clinical diagnostic tasks.

In this paper we present an extensive comparison between several feedforward neural network types in the context of a clinical diagnostic task, namely the detection of coronary artery disease (CAD) using planar thallium-201 dipyridamole stress-redistribution scintigrams. We introduce results from well-known (e.g. multilayer perceptrons or MLPs, and radial basis function networks or RBFNs) as well as novel neural network techniques (e.g. conic section function networks) which demonstrate promising new routes for future applications of neural networks in medicine, and elsewhere. In particular we show that initializations of MLPs and conic section function networks--which can learn to behave more like an MLP or more like an RBFN--can lead to much improved results in rather difficult diagnostic tasks.

Coronary Disease↗
PubMed1997

Artificial neural networks improve the accuracy of cancer survival prediction.

BACKGROUND: The TNM staging system originated as a response to the need for an accurate, consistent, universal cancer outcome prediction system. Since the TNM staging system was introduced in the 1950s, new prognostic factors have been identified and new methods for integrating prognostic factors have been developed. This study compares the prediction accuracy of the TNM staging system with that of artificial neural network statistical models. METHODS: For 5-year survival of patients with breast or colorectal carcinoma, the authors compared the TNM staging system's predictive accuracy with that of artificial neural networks (ANN). The area under the receiver operating characteristic curve, as applied to an independent validation data set, was the measure of accuracy. RESULTS: For the American College of Surgeons' Patient Care Evaluation (PCE) data set, using only the TNM variables (tumor size, number of positive regional lymph nodes, and distant metastasis), the artificial neural network's predictions of the 5-year survival of patients with breast carcinoma were significantly more accurate than those of the TNM staging system (TNM, 0.720; ANN, 0.770; P < 0.001). For the National Cancer Institute's Surveillance, Epidemiology, and End Results breast carcinoma data set, using only the TNM variables, the artificial neural network's predictions of 10-year survival were significantly more accurate than those of the TNM staging system (TNM, 0.692; ANN, 0.730; P < 0.01). For the PCE colorectal data set, using only the TNM variables, the artificial neural network's predictions of the 5-year survival of patients with colorectal carcinoma were significantly more accurate than those of the TNM staging system (TNM, 0.737; ANN, 0.815; P < 0.001). Adding commonly collected demographic and anatomic variables to the TNM variables further increased the accuracy of the artificial neural network's predictions of breast carcinoma survival (0.784) and colorectal carcinoma survival (0.869). CONCLUSIONS: Artificial neural networks are significantly more accurate than the TNM staging system when both use the TNM prognostic factors alone. New prognostic factors can be added to artificial neural networks to increase prognostic accuracy further. These results are robust across different data sets and cancer sites.

Breast Neoplasms↗
PubMed1999

A learning algorithm for oscillatory cellular neural networks.

We present a cellular type oscillatory neural network for temporal segregation of stationary input patterns. The model comprises an array of locally connected neural oscillators with connections limited to a 4-connected neighborhood. The architecture is reminiscent of the well-known cellular neural network that consists of local connection for feature extraction. By means of a novel learning rule and an initialization scheme, global synchronization can be accomplished without incurring any erroneous synchrony among uncorrelated objects. Each oscillator comprises two mutually coupled neurons, and neurons share a piecewise-linear activation function characteristic. The dynamics of traditional oscillatory models is simplified by using only one plastic synapse, and the overall complexity for hardware implementation is reduced. Based on the connectedness of image segments, it is shown that global synchronization and desynchronization can be achieved by means of locally connected synapses, and this opens up a tremendous application potential for the proposed architecture. Furthermore, by using special grouping synapses it is demonstrated that temporal segregation of overlapping gray-level and color segments can also be achieved. Finally, simulation results show that the learning rule proposed circumvents the problem of component mismatches, and hence facilitates a large-scale integration.

Journal Article↗
PubMed1992

Evidence of hyperplanes in the genetic learning of neural networks.

Genetic Algorithms have been successfully applied to the learning process of neural networks simulating artificial life. In previous research we compared mutation and crossover as genetic operators on neural networks directly encoded as real vectors (Manczer and Parisi 1990). With reference to crossover we were actually testing the building blocks hypothesis, as the effectiveness of recombination relies on the validity of such hypothesis. Even with the real genotype used, it was found that the average fitness of the population of neural networks is optimized much more quickly by crossover than it is by mutation. This indicated that the intrinsic parallelism of crossover is not reduced by the high cardinality, as seems reasonable and has indeed been suggested in GA theory (Antonisse 1989). In this paper we first summarize such findings and then propose an interpretation in terms of the spatial correlation of the fitness function with respect to the metric defined by the average steps of the genetic operators. Some numerical evidence of such interpretation is given, showing that the fitness surface appears smoother to crossover than it does to mutation. This confirms indirectly that crossover moves along privileged directions, and at the same time provides a geometric rationale for hyperplanes.

Algorithms↗
PubMed2005

The dynamic wave expansion neural network model for robot motion planning in time-varying environments.

We introduce a new type of neural network--the dynamic wave expansion neural network (DWENN)--for path generation in a dynamic environment for both mobile robots and robotic manipulators. Our model is parameter-free, computationally efficient, and its complexity does not explicitly depend on the dimensionality of the configuration space. We give a review of existing neural networks for trajectory generation in a time-varying domain, which are compared to the presented model. We demonstrate several representative simulative comparisons as well as the results of long-run comparisons in a number of randomly-generated scenes, which reveal that the proposed model yields dominantly shorter paths, especially in highly-dynamic environments.

Central Nervous System↗
PubMed2005

State estimation for delayed neural networks.

In this letter, the state estimation problem is studied for neural networks with time-varying delays. The interconnection matrix and the activation functions are assumed to be norm-bounded. The problem addressed is to estimate the neuron states, through available output measurements, such that for all admissible time-delays, the dynamics of the estimation error is globally exponentially stable. An effective linear matrix inequality approach is developed to solve the neuron state estimation problem. In particular, we derive the conditions for the existence of the desired estimators for the delayed neural networks. We also parameterize the explicit expression of the set of desired estimators in terms of linear matrix inequalities (LMIs). Finally, it is shown that the main results can be easily extended to cope with the traditional stability analysis problem for delayed neural networks. Numerical examples are included to illustrate the applicability of the proposed design method.

Algorithms↗
PubMed2001

On the inter-relations between artificial and physiological neural networks.

This paper discusses the inter-relations between findings on the physiological neural network (PNN) and artificial neural networks (ANN). It discusses the interaction of progress in both PNN and ANN for the purpose of borrowing from ANN's mathematical understandings to establish pointers for further explorations to better understand the PNN, and also for the reciprocal transferring of knowledge from PNN findings to improve ANN schemes. Such improvements in ANN are essential for better handling the needs of the information technology (IT) explosion in dealing with huge data bases and where data often defy analysis and are incomplete and fuzzy. On the other hand, principles and elements of ANN designs that appear to be important and successful can serve as guides for identifying them in the PNN, to be subsequently confirmed by bioanalytical tests. Hence progress in PNN is obviously essential for progress in ANN, as is progress in ANN helpful in PNN modeling, though its laboratory confirmation is still a far lengthier process. We discuss certain specific ANN schemes with respect to the above inter-relations with PNN. We feel that the progress in both PNN and ANN research provides a major link between the thrust in information technology developments and the thrust in biological science research, which are most probably the two major focus areas of research at the dawn of the 21st century.

Animals↗