2003/09/07 by Petro M. Gopych
Computer Science · Biochemistry, Genetics and Molecular Biology · #cs.AI #cs.IR #q-bio.NC #q-bio.QM
published as International Journal on Information Theories & Applications, 2003, vol. 10, no.2, pp.189-197. · Proceedings of the KDS-2003 Conference held in Varna, Bulgaria on June 16-26, 2003, pages 138-146, 5 Figures, 18 references
arxiv created 2003/09/07 · arxiv updated 2009/12/01
On 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.