Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “neural networks”

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 19 recordsLinked to original sources
PubMed2001

Pattern classification by a condensed neural network.

Neural networks have come to the fore as potent pattern classifiers. More amenable to parallel computation, they are much faster than the nearest neighbor classifier (NN), which, however, has distinctly outperformed them in several applications. The purpose of this study is to investigate a condensed neural network that combines the classification speed of neural networks and the low error rate of the nearest neighbor classifier. This condensed network is a fast, accurate classifier of simple architecture and function: it consists of a set of generalized perceptrons that draw maximal hyperspherical boundaries centered on patterns of memory units, each circumscribing reference patterns of a single category. The generalized perceptrons carry out classification, assisted by sporadic nearest neighbor matching to patterns of a small reference set. We compare the condensed network to a high performance neural network pattern classifier (Kohonen) and to NN in experiments on hand-printed character recognition.

Neural Networks, Computer↗
PubMedDate not supplied

[Formation of diagnostic rules by using neural networks].

Neural networks were trained on unrepresentative patient data sets proposed by skilled clinicians. In all cases, the trained neural networks correctly classified all presented cases. There were 2 intervals introduced for encoding estimates. The number of both signs and neurons in the trained neural networks was minimized. The trained neural networks adequately represent a set of logical formulas that are easy to perceive. These formulas are similar to syndrome complexes, they can be tabulated and presented as diagnostic tables the physicians usually use. The proposed decisions are accompanied by the estimates of their affinity, which allows their validity to be controlled. The clinical studies performed showed that the proposed decisions were in good agreement with medical conclusions in most cases (over 88%).

Cardiomyopathies↗
PubMed2004

A machine learning method for extracting symbolic knowledge from recurrent neural networks.

Neural networks do not readily provide an explanation of the knowledge stored in their weights as part of their information processing. Until recently, neural networks were considered to be black boxes, with the knowledge stored in their weights not readily accessible. Since then, research has resulted in a number of algorithms for extracting knowledge in symbolic form from trained neural networks. This article addresses the extraction of knowledge in symbolic form from recurrent neural networks trained to behave like deterministic finite-state automata (DFAs). To date, methods used to extract knowledge from such networks have relied on the hypothesis that networks' states tend to cluster and that clusters of network states correspond to DFA states. The computational complexity of such a cluster analysis has led to heuristics that either limit the number of clusters that may form during training or limit the exploration of the space of hidden recurrent state neurons. These limitations, while necessary, may lead to decreased fidelity, in which the extracted knowledge may not model the true behavior of a trained network, perhaps not even for the training set. The method proposed here uses a polynomial time, symbolic learning algorithm to infer DFAs solely from the observation of a trained network's input-output behavior. Thus, this method has the potential to increase the fidelity of the extracted knowledge.

Algorithms↗
PubMed2002

Biologic models of traumatic memories and post-traumatic stress disorder. The role of neural networks.

Neural networks and their behavior provide an information-processing model for initiation and maintenance of the biologic aspects of post-traumatic stress disorder (PTSD). The repeated replaying of the intrusive and distressing recollections that follow a trauma modifies the structure of the neural networks involved in the processing of traumatic memories. The hypothesis is proposed that this repetition instigates the mechanisms of iterative learning, top-down activation and pruning. The development of the symptoms of PTSD can be explained by current knowledge about modeling disturbances of parallel distributing processing. The noradrenergic neurons play a central role in coordinating the interaction of multiple cortical regions, which is an essential aspect of parallel distributed processing. Disturbances of this system in PTSD are likely to be manifest as a dysfunctional modulation of working memory and involuntary traumatic recollection. Modifications of neural networks have a secondary effect of kindling in the hippocampus that further moderates the individual's sensitivity to a range of stressors. Therefore, a neural network model of PTSD provides a method for conceptualizing the onset of PTSD symptoms and their subsequent modification with the passage of time.

Animals↗
PubMed1999

Classification of ion mobility spectra by functional groups using neural networks.

Neural networks were trained using whole ion mobility spectra from a standardized database of 3137 spectra for 204 chemicals at various concentrations. Performance of the network was measured by the success of classification into ten chemical classes. Eleven stages for evaluation of spectra and of spectral pre-processing were employed and minimums established for response thresholds and spectral purity. After optimization of the database, network, and pre-processing routines, the fraction of successful classifications by functional group was 0.91 throughout a range of concentrations. Network classification relied on a combination of features, including drift times, number of peaks, relative intensities, and other factors apparently including peak shape. The network was opportunistic, exploiting different features within different chemical classes. Application of neural networks in a two-tier design where chemicals were first identified by class and then individually eliminated all but one false positive out of 161 test spectra. These findings establish that ion mobility spectra, even with low resolution instrumentation, contain sufficient detail to permit the development of automated identification systems.

Alcohols↗
PubMed2006

Invariance priors for Bayesian feed-forward neural networks.

Neural networks (NN) are famous for their advantageous flexibility for problems when there is insufficient knowledge to set up a proper model. On the other hand, this flexibility can cause overfitting and can hamper the generalization of neural networks. Many approaches to regularizing NN have been suggested but most of them are based on ad hoc arguments. Employing the principle of transformation invariance, we derive a general prior in accordance with the Bayesian probability theory for feed-forward networks. An optimal network is determined by Bayesian model comparison, verifying the applicability of this approach. Additionally the prior presented affords cell pruning.

Algorithms↗
PubMed2005

Comparison of recent methods for inference of variable influence in neural networks.

Neural networks (NNs) belong to 'black box' models and therefore 'suffer' from interpretation difficulties. Four recent methods inferring variable influence in NNs are compared in this paper. The methods assist the interpretation task during different phases of the modeling procedure. They belong to information theory (ITSS), the Bayesian framework (ARD), the analysis of the network's weights (GIM), and the sequential omission of the variables (SZW). The comparison is based upon artificial and real data sets of differing size, complexity and noise level. The influence of the neural network's size has also been considered. The results provide useful information about the agreement between the methods under different conditions. Generally, SZW and GIM differ from ARD regarding the variable influence, although applied to NNs with similar modeling accuracy, even when larger data sets sizes are used. ITSS produces similar results to SZW and GIM, although suffering more from the 'curse of dimensionality'.

Algorithms↗
PubMed1997

Optimal Linear Combinations of Neural Networks.

Neural network-based modeling often involves trying multiple networks with different architectures and training parameters in order to achieve acceptable model accuracy. Typically, one of the trained networks is chosen as best, while the rest are discarded. [Hashem and Schmeiser (1995)] proposed using optimal linear combinations of a number of trained neural networks instead of using a single best network. Combining the trained networks may help integrate the knowledge acquired by the components networks and thus improve model accuracy. In this paper, we extend the idea of optimal linear combinations (OLCs) of neural networks and discuss issues related to the generalization ability of the combined model. We then present two algorithms for selecting the component networks for the combination to improve the generalization ability of OLCs. Our experimental results demonstrate significant improvements in model accuracy, as a result of using OLCs, compared to using the apparent best network. Copyright 1997 Elsevier Science Ltd.

Journal Article↗
PubMedDate not supplied

Entropic analysis and incremental synthesis of multilayered feedforward neural networks.

Neural network architecture optimization is often a critical issue, particularly when VLSI implementation is considered. This paper proposes a new minimization method for multilayered feedforward ANNs and an original approach to their synthesis, both based on the analysis of the information quantity (entropy) flowing through the network. A layer is described as an information filter which selects the relevant characteristics until the complete classification is performed. The basic incremental synthesis method, including the supervised training procedure, is derived to design application-tailored neural paradigms with good generalization capability.

Algorithms↗
PubMed2000

Optimization of chemical libraries by neural networks.

Neural networks are finding ever-more applications in the design of combinatorial libraries. These can be divided into two types: Kohonen (self-organizing) maps, and feed-forward networks. While the number of applications is currently quite limited, a rapid increase in publications in this area can be expected in the next few years from the rapid development of general combinatorial chemistry technology.

Combinatorial Chemistry Techniques↗
PubMed2000

Estimating germinability of Plasmopara viticola oospores by means of neural networks.

Neural networks are trained to estimate the germination percentages of Plasmopara viticola oospores, overwintered in natural conditions in two viticultural areas in northern Italy, by using climatic (temperature and rainfall) data, as well as the previous germination measurement, as input variables. The 288 available patterns consist of a set of selected independent variables associated with the corresponding germination percentage. All 12 networks investigated converge to a non-linear relationship between the selected independent variables and oospore germination. The highest correlation coefficient (equal to 0.83) between the real and estimated germination percentages is obtained by considering, as input to the network, the climatic data (both temperature and rainfall) recorded during the 40 days before sampling and the germination percentage assessed in the germination assay carried out immediately before the present sampling.

Germination↗
PubMed1995

Multicomponent kinetic determinations using artificial neural networks.

Neural networks were successfully used for multicomponent kinetic determinations of species with rate constant ratios approaching unity without the aid of spectral discrimination. The ensuing method relies on two inputs describing the profile of the kinetic curve for each mixture, which is obtained by preprocessing kinetic data using nonlinear least-squares regression. A straightforward network architecture (2:4s:21) was used to resolve mixtures of 2- and 3-chlorophenol; the trained network estimated the concentrations of both components in the mixture with a relative standard error of prediction of approximately 5%, which is much lower than that obtained with Kalman filtering. The effect of some variables such as the rate constant and analyte concentration ratios on the proposed multicomponent determination is discussed.

Chlorophenols↗