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.

SourceResearch connectionFrom yearThrough year

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

At least 1,315 records · Page 73Linked to original sources

PubMed1993

Neural networks, nativism, and the plausibility of constructivism.

Recent interest in PDP (parallel distributed processing) models is due in part to the widely held belief that they challenge many of the assumptions of classical cognitive science. In the domain of language acquisition, for example, there has been much interest in the claim that PDP models might undermine nativism. Related arguments based on PDP learning have also been given against Fodor's anti-constructivist position--a position that has contributed to the widespread dismissal of constructivism. A limitation of many of the claims regarding PDP learning, however, is that the principles underlying this learning have not been rigorously characterized. In this paper, I examine PDP models from within the framework of Valiant's PAC (probably approximately correct) model of learning, now the dominant model in machine learning, and which applies naturally to neural network learning. From this perspective, I evaluate the implications of PDP models for nativism and Fodor's influential anti-constructivist position. In particular, I demonstrate that, contrary to a number of claims, PDP models are nativist in a robust sense. I also demonstrate that PDP models actually serve as a good illustration of Fodor's anti-constructivist position. While these results may at first suggest that neural network models in general are incapable of the sort of concept acquisition that is required to refute Fodor's anti-constructivist position, I suggest that there is an alternative form of neural network learning that demonstrates the plausibility of constructivism. This alternative form of learning is a natural interpretation of the constructivist position in terms of neural network learning, as it employs learning algorithms that incorporate the addition of structure in addition to weight modification schemes. By demonstrating that there is a natural and plausible interpretation of constructivism in terms of neural network learning, the position that nativism is the only plausible model of acquisition can no longer be defended. Indeed, I briefly discuss a number of learning-theoretic reasons indicating that constructivist models so characterized uniquely possess a number of important learning characteristics.

Cognition↗

PubMed1996

Multi-layer neural network analysis of cerebrospinal fluid pressure patterns in idiopathic normal-pressure hydrocephalus.

The cerebrospinal fluid (CSF) pressure patterns have been reported as one of the most relevant indexes for the diagnosis and treatment of idiopathic normal-pressure hydrocephalus (INPH). Forty consecutive patients coming from our observations with the classic Hakim's triad underwent continuous CSF pressure monitoring via lumbar puncture for at least 12 hours. Twenty-eight patients were diagnosed as having INPH and underwent CSF shunt. A multi-layer neural network (perceptron) was employed to study the pressure patterns in order to try an alternative classification to the "expert" neurosurgeon one. Differences between expert and neural network classifications were indeed observed. Such differences may depend on the small group studied or on the inadequacy of CFS pressure patterns in correctly individuating those INPH patients who benefit from shunt surgery. The authors think that neural network processing of INPH could add relevant information to select the "responder" patients to surgery: in fact neural networks represent a powerful methodology for aiding the expert to select the proper choice on the basis of "what learnt" by the networks themselves.

Cerebrospinal Fluid↗

PubMed1997

Neural networks analysis of astrocytic gliomas from MRI appearances.

A three-layered backpropagation neural network was developed to differentiate malignant from benign brain tumors in a group of patients with astrocytic gliomas. The MRI findings of 43 patients were reviewed before biopsy by three neuroradiologists independently. This provided a database made up of 129 patients' records each of which comprised 13 parameters derived from pre- and post-contrast MR images. The network's generalizing ability was then tested to predict the outcome of biopsy in 36 new cases and its performance compared to that of radiologist using ROC analysis. The output of the network with and without radiologists' impression yielded a better diagnostic performance with relative ROC areas of 0.94 and 0.91, respectively; compared to 0.84 obtained by radiologist. These results demonstrate that the neural network can effectively differentiate malignant from benign brain tumors.

Algorithms↗

PubMed1997

Variational Approach to Unsupervised Learning Algorithms of Neural Networks.

Variational approach in pattern recognition basing on a mean risk functional is applied to unsupervised learning algorithms for neural networks. The paper summarizes main statements and results of the approach: a structure of mean risk functionals relevant for the problem of grouping the multivariate data; optimum conditions; recurrent algorithms of stochastic approximation type for minimization of the functionals; and conditions ensuring convergence of the algorithms to appropriate solutions. Basing on this theory a general scheme is proposed and it allows to obtain neural networks whose adaptation laws arise as the recurrent unsupervised learning algorithms for suitably selected mean risk functionals. The well known Grossberg networks, counter-propagation networks, and Kohonen self-organizing networks are among them. Moreover the new variants of unsupervised-learning neural structures can be derived as it is demonstrated in the paper. The developed mathematical means can serve for theoretical justification of using such neural networks in data processing systems. Copyright 1997 Elsevier Science Ltd. All Rights Reserved.

Journal Article↗

PubMed2000

A computerized mastitis decision aid using farm-based records: an artificial neural network approach.

A computer module was developed and tested that used field survey and Dairy Herd Improvement Association (DHIA) data to broadly classify bacterial causes of mastitis in dairy herds. Further development of the computer model could aid interpretation of DHIA data by dairy record processing centers and herd consultants. This diagnostic module was developed with an artificial neural network, a technology that processes complex data in a manner similar to human brain function. Information describing herd management practices, quarter milk samples, and monthly DHIA data was collected from Pennsylvania dairy herds with moderate to high somatic cell counts. This information was used to develop or train an artificial neural network model that discriminated among four categories of bacterial organisms (contagious, environmental, no significant growth, and other) associated with clinical and subclinical mastitis. After training the model, new DHIA and management data were presented to the model to assess its ability to classify bacteriological etiology. When the artificial neural network was used, the probabilities of diagnosing the bacteriologic status from three randomly selected cow groups and from new untested herds ranged from 57 to 71%. Performance of the artificial neural network model was best in herds with higher frequency of minor and contagious pathogens. Prediction results for the same test data with linear discriminant analysis were less successful, ranging from 42 to 57%.

Animals↗

PubMed1996

Nonlinear time series analysis by neural networks: a case study.

This paper presents a neural network approach to time-series analysis of a univariate nonlinear system. Feedforward networks are studied, and an appropriate network size is determined by different criteria computed on the basis of the performance of the models on the training and test sets. The analysis and conclusions drawn are supported by studies of the phase portraits of the models. By a proper choice of network size, the problems of over-parameterization are demonstrated to be avoided. The overfitting observed for larger networks is analyzed and the underlying reasons for their worse generalization capabilities are explained. Finally, some observations are made on the approximation provided by an oversized network with weights determined by an incomplete (interrupted) training and that of the optimal-sized network.

Cybernetics↗

PubMed2006

Training reformulated radial basis function neural networks capable of identifying uncertainty in data classification.

This paper introduces a learning algorithm that can be used for training reformulated radial basis function neural networks (RBFNNs) capable of identifying uncertainty in data classification. This learning algorithm trains a special class of reformulated RBFNNs, known as cosine RBFNNs, by updating selected adjustable parameters to minimize the class-conditional variances at the outputs of their radial basis functions (RBFs). The experiments verify that quantum neural networks (QNNs) and cosine RBFNNs trained by the proposed learning algorithm are capable of identifying uncertainty in data classification, a property that is not shared by cosine RBFNNs trained by the original learning algorithm and conventional feed-forward neural networks (FFNNs). Finally, this study leads to a simple classification strategy that can be used to improve the classification accuracy of QNNs and cosine RBFNNs by rejecting ambiguous feature vectors based on their responses.

Algorithms↗

PubMed2005

Prediction of minor head injured patients using logistic regression and MLP neural network.

In this study it is aimed to assess the posttraumatic cerebral hemodynamia in minor head injured patients. Eighty patients with minor head injury (Group 1) evaluated in the early 8 h of posttraumatic period between July 2003 and February 2004. The control group (Group 2) has composed of 32 healthy people. Bilateral blood flow velocities of middle cerebral arteries (MCA) had measured using transtemporal technique while internal carotid arteries were evaluated by submandibular examination. Two different mathematical models such as the traditional statistical method on the basis of logistic regression and a multi-layer perceptron (MLP) neural network are used to classify the age, sex, velocitiy parameters of MCA, mean velocity of extracranial ICAs and V(MCA)/ V(ICA) ratios. The neural network was trained, cross-validated and tested with subject's transcranial Doppler signals. As a result of these classifications, we found the success rate of logistic regression, the success rate of MLP neural network is 88.2 and 89.1%, respectively. The classification results show that MLP neural network is offering the best results in the case of diagnosis.

Age Factors↗

PubMed2005

Global exponential periodicity of a class of recurrent neural networks with oscillating parameters and time-varying delays.

In this paper, we present the analytical results on the global exponential periodicity of a class of recurrent neural networks with oscillating parameters and time-varying delays. Sufficient conditions are derived for ascertaining the existence, uniqueness and global exponential periodicity of the oscillatory solution of such recurrent neural networks by using the comparison principle and mixed monotone operator method. The periodicity results extend or improve existing stability results for the class of recurrent neural networks with and without time delays.

Animals↗

PubMed1996

Artificial neural networks as a novel approach to integrated pharmacokinetic-pharmacodynamic analysis.

A novel model-independent approach to analyze pharmacokinetic (PK)-pharmacodynamic (PD) data using artificial neural networks (ANNs) is presented. ANNs are versatile computational tools that possess the attributes of adaptive learning and self-organization. The emulative ability of neural networks is evaluated with simulated PK-PD data, and the power of ANNs to extrapolate the acquired knowledge is investigated. ANNs of one architecture are shown to be flexible enough to accurately predict PD profiles for a wide variety of PK-PD relationships (e.g., effect compartment linked to the central or peripheral compartment and indirect response models). Also, an example is given of the ability of ANNs to accurately predict PD profiles without requiring any information regarding the active metabolite. Because structural details are not required, ANNs exhibit a clear advantage over conventional model-dependent methods. ANNs are proved to be robust toward error in the data and perturbations in the initial estimates. Moreover, ANNs were shown to handle sparse data well. Neural networks are emerging as promising tools in the field of drug discovery and development.

Mathematical Computing↗

PubMed2004

Markovian architectural bias of recurrent neural networks.

In this paper, we elaborate upon the claim that clustering in the recurrent layer of recurrent neural networks (RNNs) reflects meaningful information processing states even prior to training [1], [2]. By concentrating on activation clusters in RNNs, while not throwing away the continuous state space network dynamics, we extract predictive models that we call neural prediction machines (NPMs). When RNNs with sigmoid activation functions are initialized with small weights (a common technique in the RNN community), the clusters of recurrent activations emerging prior to training are indeed meaningful and correspond to Markov prediction contexts. In this case, the extracted NPMs correspond to a class of Markov models, called variable memory length Markov models (VLMMs). In order to appreciate how much information has really been induced during the training, the RNN performance should always be compared with that of VLMMs and NPMs extracted before training as the "null" base models. Our arguments are supported by experiments on a chaotic symbolic sequence and a context-free language with a deep recursive structure. Index Terms-Complex symbolic sequences, information latching problem, iterative function systems, Markov models, recurrent neural networks (RNNs).

Markov Chains↗

PubMed1996

A neural network model forecasting for prediction of daily maximum ozone concentration in an industrialized urban area.

Prediction of ambient ozone concentrations in urban areas would allow evaluation of such factors as compliance and noncompliance with EPA requirements. Though ozone prediction models exist, there is still a need for more accurate models. Development of these models is difficult because the meteorological variables and photochemical reactions involved in ozone formation are complex. In this study, we developed a neural network model for forecasting daily maximum ozone levels. We then compared the neural network's performance with those of two traditional statistical models, regression, and Box-Jenkins ARIMA. The neural network model for forecasting daily maximum ozone levels is different from the two statistical models because it employs a pattern recognition approach. Such an approach does not require specification of the structural form of the model. The results show that the neural network model is superior to the regression and Box-Jenkins ARIMA models we tested.

Journal Article↗

PubMed1996

Application of neural networks to quantitative nondestructive evaluation.

This paper concentrates on the quantitative analysis of reflection and transmission characteristics of structural waves in notched beams using neural networks. At one end of a rod a piezoelectric transducer excites a flexural guided wave, which propagates through the structure and is reflected from the notch as well as from the ends of the rod. At another point, a laser interferometer measures the resulting displacement versus time, which is recorded and serves as the digital fingerprint of the experiment. Our aim is to obtain quantitative information about the notch characteristics, i.e. its location and depth, on the basis of these digital recordings. This requires an inverse problem to be solved using neural networks. For the training of the network, synthetically produced wave patterns are used. The results of the corresponding wave experiment simulations compare well with experimental data. For fixed location, the calculated wave patterns could be quantitatively analysed to yield the depth of the notch if it is greater than a twentieth of the diameter. Another network could be trained for the localization with an accuracy of 2 cm for 93% of the training patterns. On the basis of these results a strategy is formulated on how neural networks could be trained to evaluate quantitatively both of the notch characteristics.

Algorithms↗

PubMed1996

Artificial neural network to assist psychiatric diagnosis.

BACKGROUND: Artificial Neural Network (ANN), as a potential powerful classifier, was explored to assist psychiatric diagnosis of the Composite International Diagnostic Interview (CIDI). METHOD: Both Back-Propagation (BP) and Kohonen networks were developed to fit psychiatric diagnosis and programmed (using 60 cases) to classify neurosis, schizophrenia and normal people. The programmed networks were cross-tested using another 222 cases. All subjects were randomly selected from two mental hospitals in Beijing. RESULTS: Compared to ICD-10 diagnosis by psychiatrists, the overall kappa of BP network was 0.94 and that of Kohonen was 0.88 (both P < 0.01). In classifying patients who were difficult to diagnose, the kappa of BP was 0.69 (P < 0.01). ANN-assisted CIDI was compared with expert system assisted CIDI (kappa = 0.72-0.76); ANN was more powerful than a traditional expert system. CONCLUSION: ANN might be used to improve psychiatric diagnosis.

Adult↗

PubMed1991

Color categorization and color constancy in a neural network model of V4.

We develop a neural network model that instantiates color constancy and color categorization in a single unified framework. Previous models achieve similar effects but ignore important biological constraints. Color constancy in this model is achieved by a new application of the double opponent cells found in the "blobs" of the visual cortex. Color categorization emerges naturally, as a consequence of processing chromatic stimuli as vectors in a four-dimensional color space. A computer simulation of this model is subjected to the classic psychophysical tests that first uncovered these phenomena, and its response matches psychophysical results very closely.

Animals↗

PubMed2003

Neural networks for the prediction of spirometric reference values.

Normal lung function values are conventionally calculated according to prediction equations. The primary objective of this study is the development of a different method for the prediction of FVC and FEV1 parameters, in order to achieve better correlation of the predicted values to the real ones. Using a sample from the Greek elderly population that was separated into two groups (a training and a testing one), a number of artificial neural networks were trained. Considering that men and women were studied separately and that two parameters (FVC, FEV1) were the target of the study, four cases came up. In each case two neural networks were trained using different transfer functions, number of neurons and number of layers. When passing the inputs of the testing data set to the trained networks it was found that the outputs were well correlated with the corresponding measures of the sample. Furthermore, the match with the sample, for a number of neural networks developed, was better compared to the matches of Baltopoulos et al. study that used the same sample for developing prediction equations. This high match allows the potential use of neural networks for predicting not only FVC and FEV1 but also other spirometric parameters.

Aged↗

PubMed2001

Modeling acute toxicity of chemicals to Daphnia magna: a probabilistic neural network approach.

A methodology based on probabilistic neural networks (PNNs) is applied to model the acute toxicity (48-h LC50) of a set of 700 highly diverse chemicals to Daphnia magna. First, cross-validation experiments confirming the potential use of the PNN as modeling tool for the problem at hand were performed. Next, various approaches to construct-improved models are presented. The resulting four models are then validated using an external test set of 76 additional compounds. Input to the PNNs is derived solely from simple molecular descriptors and structural fragments and excludes bulk property parameters, such as the water solubility or the octanol/water partition coefficient.

Animals↗

PubMed1995

Improved classification of psychiatric mood disorders using a feedforward neural network.

Our aim was to use a neural network model for classifying psychiatric mood disorders. In approaching this interdisciplinary task, the concern was not to build a more biologically plausible model, but to test the computational capabilities of an existent one. The multilayer perceptron was chosen as a model, trained and tested using both theoretical and real cases. The classification proved to be good, but we are aware of the fact that both training and testing should be performed in the future only on real data, as the way to get a true picture of the system's performance.

Adult↗