Search results for "associative memory"

showing 4 items of 4 documents

Sliding Intermittent Control for BAM Neural Networks with Delays

2013

Published version of an article in the journal: Abstract and Applied Analysis. Also available from the publisher at: http://dx.doi.org/10.1155/2013/615947 Open Access This paper addresses the exponential stability problem for a class of delayed bidirectional associative memory (BAM) neural networks with delays. A sliding intermittent controller which takes the advantages of the periodically intermittent control idea and the impulsive control scheme is proposed and employed to the delayed BAM system. With the adjustable parameter taking different particular values, such a sliding intermittent control method can comprise several kinds of control schemes as special cases, such as the continuou…

Lyapunov functionArticle SubjectArtificial neural networklcsh:MathematicsApplied MathematicsIntermittent controllcsh:QA1-939symbols.namesakeExponential stabilityControl theorysymbolsContinuous feedbackBidirectional associative memoryVDP::Matematikk og Naturvitenskap: 400::Matematikk: 410::Analyse: 411AnalysisMathematics
researchProduct

The inhibitory effect of long-term associative representation on working memory

2020

Studies on how long-term memory affects working memory (WM) have found that long-term memory can enhance WM processing. However, these studies only use item memory as the representation of long-term memory. In addition to item memory, associative memory is also an essential part of long-term memory. The associative memory and item memory involve different cognitive mechanisms and brain areas. The purpose of the present study was to investigate how associative memory affects WM processing. Before the WM task, participants were asked to store 16 pairs of dissimilar pictures into long-term memory. The participants would obtain the associative memory of these pairs of pictures in the long-term …

alpha powerassociative memoryWorking memoryLong-term memoryComputer scienceRepresentation (systemics)Content-addressable memorysäilömuistityömuistikognitiiviset prosessitworking memoryTerm (time)long-term memoryassosiaatioAlpha powerInhibitory effectGeneral PsychologyAssociative propertyCognitive psychologymuisti (kognitio)
researchProduct

What represents a face? A computational approach for the integration of physiological and psychological data.

1997

Empirical studies of face recognition suggest that faces might be stored in memory by means of a few canonical representations. The nature of these canonical representations is, however, unclear. Although psychological data show a three-quarter-view advantage, physiological studies suggest profile and frontal views are stored in memory. A computational approach to reconcile these findings is proposed. The pattern of results obtained when different views, or combinations of views, are used as the internal representation of a two-stage identification network consisting of an autoassociative memory followed by a radial-basis-function network are compared. Results show that (i) a frontal and a…

050109 social psychologyExperimental and Cognitive PsychologyFacial recognition system050105 experimental psychologyAutoassociative memoryConnectionismArtificial IntelligenceMemoryImage Processing Computer-AssistedHumans0501 psychology and cognitive sciencesComputer SimulationRecognition memoryCommunicationArtificial neural networkbusiness.industryMemoria05 social sciencesCognitionSensory SystemsForm PerceptionOphthalmologyIdentification (information)FacePsychologybusinessCognitive psychologyPerception
researchProduct

Sex Classification of Face Areas

1998

Human subjects and an artificial neural network, composed of an autoassociative memory and a perceptron, gender classified the same 160 frontal face images (80 male and 80 female). All 160 face images were presented under three conditions (1) full face image with the hair cropped (2) top portion only of the Condition 1 image (3) bottom portion only of the Condition 1 image. Predictions from simulations using Condition 1 stimuli for training and testing novel stimuli in Conditions 1, 2, and 3, were compared to human subject performance. Although the network showed a fair ability to generalize learning to new stimuli under the three conditions, performing from 66 to 78% correctly on novel fa…

Image areaEcologyArtificial neural networkComputer sciencebusiness.industryApplied MathematicsPattern recognitionGeneral MedicinePerceptronAgricultural and Biological Sciences (miscellaneous)Image (mathematics)Autoassociative memoryFace (geometry)Human taxonomyRelevance (information retrieval)Artificial intelligencebusinessJournal of Biological Systems
researchProduct