ROC Curves Within the Framework of Neural Network Assembly Memory Model: Some Analytic Results

Simple item page
dc.creatorGopych, Petro M.
dc.date2003-09-07
dc.date.accessioned2026-07-07T03:20:17Z
dc.date.available2026-07-07T03:20:17Z
dc.descriptionOn the basis of convolutional (Hamming) version of recent Neural Network Assembly Memory Model (NNAMM) for intact two-layer autoassociative Hopfield network optimal receiver operating characteristics (ROCs) have been derived analytically. A method of taking into account explicitly a priori probabilities of alternative hypotheses on the structure of information initiating memory trace retrieval and modified ROCs (mROCs, a posteriori probabilities of correct recall vs. false alarm probability) are introduced. The comparison of empirical and calculated ROCs (or mROCs) demonstrates that they coincide quantitatively and in this way intensities of cues used in appropriate experiments may be estimated. It has been found that basic ROC properties which are one of experimental findings underpinning dual-process models of recognition memory can be explained within our one-factor NNAMM.
dc.descriptionProceedings of the KDS-2003 Conference held in Varna, Bulgaria on June 16-26, 2003, pages 138-146, 5 Figures, 18 references
dc.identifierhttps://arxiv.org/abs/cs/0309007
dc.identifierhttp://arxiv.org/abs/cs/0309007
dc.identifierInternational Journal on Information Theories & Applications, 2003, vol. 10, no.2, pp.189-197.
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/31772
dc.subjectArtificial Intelligence
dc.subjectInformation Retrieval
dc.subjectNeurons and Cognition
dc.subjectQuantitative Methods
dc.subjectI.2; E.4; J.3; J.4
dc.titleROC Curves Within the Framework of Neural Network Assembly Memory Model: Some Analytic Results
dc.typetext

Files

Collections

arXiv