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 1,171 records · Page 65Linked to original sources
PubMed2004

Analysis of perfect mappings of the stimuli through neural temporal sequences.

The analysis of an optimal neural system that maps stimuli into unique sequences of activations of fundamental atoms or functional clusters (FCs) is carried out. We say that it is perfect because the system maps with an injective function every stimulus in minimum time with the least number of FCs, such that every FC is activated only once. The neural system has the possibility to sustain several sequences in parallel. In this framework, we study the capacity achievable by the system, minimal completion time and complexity in terms of the number of parallel sequences. We show that the maximum capacity of the system is achieved without using parallel sequences at the expense of long completion times. However, when the capacity value is fixed, the largest possible number of parallel sequences is optimal because it requires short completion times. The complexity measure adds to important points: (i) the largest complexity of the system is achieved without parallel sequences, and (ii) the capacity estimation is a good estimation of the complexity of the system.

Algorithms↗
PubMedDate not supplied

A simple cell model with dominating opponent inhibition for robust image processing.

The extraction of oriented contrast information by cortical simple cells is a fundamental step in early visual processing. The orientation selectivity originates at least partly from the input of lateral geniculate nuclei neurons with properly aligned receptive fields. In the present article, we investigate the feedforward interactions between on- and off-pathways. Based on physiological evidence we propose a push-pull model with dominating opponent inhibition (DOI). We show that the model can account for empirical data on simple cells, such as contrast-invariant orientation tuning, sharpening of orientation tuning with increasing inhibition, and strong response decrements to stimuli with luminance gradient reversal. With identical parameter settings, we apply the model for the processing of synthetic and real world images. We show that the model with DOI can robustly extract oriented contrast information from noisy input. More important, noise is adaptively suppressed, i.e. the model simple cells do not respond to homogeneous regions of different noise levels, while remaining sensitive to small contrast changes. The image processing results reveal a possible functional role of the strong inhibition as observed empirically, namely to adaptively suppress responses to noisy input.

Animals↗
PubMedDate not supplied

Fully automated biomedical image segmentation by self-organized model adaptation.

In this paper, we present a fully automated image segmentation method based on an algorithm that provides adaptive plasticity in function approximation problems: the deformable (feature) map (DM) algorithm. The DM approach reduces a class of similar function approximation problems to the explicit supervised one-shot training of a single data set. This is followed by a subsequent, appropriate similarity transformation, which is based on a self-organized deformation of the underlying multidimensional probability distributions. We apply this algorithm to the real-world problem of fully automated voxel-based multispectral image segmentation, employing magnetic resonance data sets of the human brain. In contrast to previous segmentation approaches, the knowledge obtained within the segmentation procedure of a single prototypical reference data set can be re-utilized for the segmentation of new, 'similar' data employing a strategy of incremental adaptive learning based on the DM algorithm. Thus, we obtain a fully automatic segmentation method that does neither require manual contour tracing of training regions, visual classification of voxel clusters, nor any other kind of human intervention. Our application demonstrates that flexible learning by a strategy of self-organized incremental model adaptation can contribute to increase the efficiency and practicability of biomedical image processing systems.

Algorithms↗
PubMed2005

Linear recursive distributed representations.

Connectionist networks have been criticized for their inability to represent complex structures with systematicity. That is, while they can be trained to represent and manipulate complex objects made of several constituents, they generally fail to generalize to novel combinations of the same constituents. This paper presents a modification of Pollack's Recursive Auto-Associative Memory (RAAM), that addresses this criticism. The network uses linear units and is trained with Oja's rule, in which it generalizes PCA to tree-structured data. Learned representations may be linearly combined, in order to represent new complex structures. This results in unprecedented generalization capabilities. Capacity is orders of magnitude higher than that of a RAAM trained with back-propagation. Moreover, regularities of the training set are preserved in the new formed objects. The formation of new structures displays developmental effects similar to those observed in children when learning to generalize about the argument structure of verbs.

Algorithms↗
PubMed2002

Using relations within conceptual systems to translate across conceptual systems.

According to an "external grounding" theory of meaning, a concept's meaning depends on its connection to the external world. By a "conceptual web" account, a concept's meaning depends on its relations to other concepts within the same system. We explore one aspect of meaning, the identification of matching concepts across systems (e.g. people, theories, or cultures). We present a computational algorithm called ABSURDIST (Aligning Between Systems Using Relations Derived Inside Systems for Translation) that uses only within-system similarity relations to find between-system translations. While illustrating the sufficiency of a conceptual web account for translating between systems, simulations of ABSURDIST also indicate powerful synergistic interactions between intrinsic, within-system information and extrinsic information.

Algorithms↗
PubMed1998

Mapping attractor fields in face space: the atypicality bias in face recognition.

A familiar face can be recognized across many changes in the stimulus input. In this research, the many-to-one mapping of face stimuli to a single face memory is referred to as a face memory's 'attractor field'. According to the attractor field approach, a face memory will be activated by any stimuli falling within the boundaries of its attractor field. It was predicted that by virtue of its location in a multi-dimensional face space, the attractor field of an atypical face will be larger than the attractor field of a typical face. To test this prediction, subjects make likeness judgments to morphed faces that contained a 50/50 contribution from an atypical and a typical parent face. The main result of four experiments was that the morph face was judged to bear a stronger resemblance to the atypical face parent than the typical face parent. The computational basis of the atypicality bias was demonstrated in a neural network simulation where morph inputs of atypical and typical representations elicited stronger activation of atypical output units than of typical output units. Together, the behavioral and simulation evidence supports the view that the attractor fields of atypical faces span over a broader region of face space that the attractor fields of typical faces.

Face↗
PubMed2003

Identifying splicing sites in eukaryotic RNA: support vector machine approach.

We introduce a new method for splicing sites prediction based on the theory of support vector machines (SVM). The SVM represents a new approach to supervised pattern classification and has been successfully applied to a wide range of pattern recognition problems. In the process of splicing sites prediction, the statistical information of RNA secondary structure in the vicinity of splice sites, e.g. donor and acceptor sites, is introduced in order to compare recognition ratio of true positive and true negative. From the results of comparison, addition of structural information has brought no significant benefit for the recognition of splice sites and had even lowered the rate of recognition. Our results suggest that, through three cross validation, the SVM method can achieve a good performance for splice sites identification.

Algorithms↗
PubMed2002

Acoustic emission data assisted process monitoring.

Gas-liquid two-phase flows are widely used in the chemical industry. Accurate measurements of flow parameters, such as flow regimes, are the key of operating efficiency. Due to the interface complexity of a two-phase flow, it is very difficult to monitor and distinguish flow regimes on-line and real time. In this paper we propose a cost-effective and computation-efficient acoustic emission (AE) detection system combined with artificial neural network technology to recognize four major patterns in an air-water vertical two-phase flow column. Several crucial AE parameters are explored and validated, and we found that the density of acoustic emission events and ring-down counts are two excellent indicators for the flow pattern recognition problems. Instead of the traditional Fair map, a hit-count map is developed and a multilayer Perceptron neural network is designed as a decision maker to describe an approximate transmission stage of a given two-phase flow system.

Acoustics↗
PubMed1999

Genetic programming as an analytical tool for non-linear dielectric spectroscopy.

By modelling the non-linear effects of membranous enzymes on an applied oscillating electromagnetic field using supervised multivariate analysis methods, Non-Linear Dielectric Spectroscopy (NLDS) has previously been shown to produce quantitative information that is indicative of the metabolic state of various organisms. The use of Genetic Programming (GP) for the multivariate analysis of NLDS data recorded from yeast fermentations is discussed, and GPs are compared with previous results using Partial Least Squares (PLS) and Artificial Neural Nets (NN). GP considerably outperforms these methods, both in terms of the precision of the predictions and their interpretability.

Computational Biology↗
PubMed1999

Obtaining interpretable fuzzy classification rules from medical data.

For many application problems classifiers can be used to support a decision making process. In some domains-in areas like medicine especially-it is preferable not to use black box approaches. The user should be able to understand the classifier and to evaluate its results. Fuzzy rule based classifiers are especially suitable, because they consist of simple linguistically interpretable rules and do not have some of the drawbacks of symbolic or crisp rule based classifiers. Classifiers must often be created from data by a learning process, because there is not enough expert knowledge to determine their parameters completely. A simple and convenient way to learn fuzzy classifiers from data is provided by neuro-fuzzy approaches. In this paper we discuss extensions to the learning algorithms of neuro-fuzzy classification (NEFCLASS), a neuro-fuzzy approach for data analysis that we have presented before. We present interactive strategies for pruning rules and variables from a trained classifier to enhance its readability, and demonstrate our approach on a small example.

Algorithms↗
PubMed2001

Medical applications of enhanced rule-based expert systems.

The paper describes several types of efficiency enhancements of 'classical' rule-based diagnostic expert systems. The blackboard control structure enables to explore more knowledge bases of the same syntax in parallel, the taxonomy structures make fast zooming of attention possible and provide additional inference mechanism based on inheritance principles. The applicability of the enhancing techniques is documented by four case studies exploring the extended FEL-EXPERT shell in different tasks of medical decision-making. The authors consider the enhancing techniques as useful steps on the way from 'classical' diagnostic expert systems towards more complex multi-agent decision tools.

Classification↗
PubMedDate not supplied

Configurational and elemental odor mixture perception can arise from local inhibition.

Contrast enhancement via lateral inhibitory circuits is a common mechanism in sensory systems. We here employ a computational model to show that, in addition to shaping experimentally observed molecular receptive fields in the olfactory bulb, functionally lateral inhibitory circuits can also mediate the elemental and configurational properties of odor mixture perception. To the extent that odor perception can be predicted by slow-timescale neural activation patterns in the olfactory bulb, and to the extent that interglomerular inhibitory projections map onto a space of odorant similarity, the model shows that these inhibitory processes in the olfactory bulb suffice to generate the behaviorally observed inverse relationship between two odorants' perceptual similarities and the perceptual similarities between either of these same odorants and their binary mixture.

Action Potentials↗
PubMed1996

What do connectionism and social psychology offer each other?

Social psychologists can benefit from exploring connectionist or parallel distributed processing models of mental representation and process also can contribute much to connectionist theory in return. Connectionist models involve many simple processing units that send activation signals over connections. At an abstract level, the models can be described as representing concepts (as distributed patterns of activation), operating like schemas to fill in typical values for input information, reconstructing memories based on accessible knowledge rather than retrieving static representations, using flexible and context-sensitive concepts, and computing by satisfying numerous constraints in parallel. This article reviews open questions regarding connectionist models and concludes that social psychological contributions to such topics as cognition-motivation interactions may be important for the development of integrative connectionist model.

Cognition↗
PubMed2006

Decoupling functional mechanisms of adaptive encoding.

In a natural setting, adaptive mechanisms constantly modulate the encoding properties of sensory neurons in response to changes in the external environment. Recent experiments have revealed that adaptation affects both the spatiotemporal integration properties and baseline membrane potential of sensory neurons. However, the precise functional role of adaptation remains an open question, due in part to contradictory experimental results. Here, we develop a framework to characterize adaptive encoding, including a cascade model with a time-varying receptive field (reflecting spatiotemporal integration properties) and offset (reflecting baseline membrane potential), and a recursive technique for tracking changes in the model parameters during a single stimulus/response trial. Simulated and experimental responses from retinal neurons are used to track adaptive changes in receptive field structure and offset during nonstationary stimulation. Due to the nonlinear nature of spiking neurons, the parameters of the receptive field and offset must be estimated simultaneously, or changes in the offset (or even in the statistical distribution of the stimulus) can mask, confound, or create the illusion of adaptive changes in the receptive field. Our analysis suggests that these confounding effects may be at the root of the inconsistency in the literature and shows that seemingly conflicting experimental results can be reconciled within our framework.

Adaptation, Physiological↗
PubMedDate not supplied

Preservation of categorical knowledge in Alzheimer's disease: a computational account.

The distinction between knowledge of specific exemplars and knowledge of their general categories is central to much theorising on the nature of semantic memory. The dissociation between exemplar and category knowledge observed in Alzheimer's Disease (AD) would appear to support this distinction, and to suggest that different neural systems are involved in the representation of exemplar and category knowledge. We review the evidence for preserved category knowledge in the semantic memory impairment of AD, and propose an alternative interpretation, according to which category and exemplar knowledge are both represented in the same distributed neural substrate. The relative preservation of category knowledge is a consequence of the greater frequency, and hence greater robustness, of the representation of attributes shared by all or most members of a category, compared to exemplar-unique attributes. We test and confirm the computational adequacy of this hypothesis in two computer simulations.

Aged↗