Performance of BSDT decoding algorithms based on locally damaged neural networks

Authors:
Petro Gopych
Affiliations:
V.N. Karazin Kharkiv National University, Kharkiv, Ukraine
Venue:
IDEAL'06 Proceedings of the 7th international conference on Intelligent Data Engineering and Automated Learning
Year:
2006

Citing 1
Cited 2

Neural network computations with negative triggering thresholds

ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I

Minimal BSDT abstract selectional machines and their selectional and computational performance

IDEAL'07 Proceedings of the 8th international conference on Intelligent data engineering and automated learning
Psychometric functions within the framework of binary signal detection theory: coding the face identity

IDEAL'07 Proceedings of the 8th international conference on Intelligent data engineering and automated learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

Traditional signal detection theory (SDT) and recent binary signal detection theory (BSDT) provide the same basic performance functions: receiver operating characteristic (ROC) and basic decoding performance (BDP) curves. Because the BSDT may simultaneously be presented in neural network (NN), convolutional, and Hamming distance forms, it contains more parameters and its predictions are richer. Here we discuss a formal definition of one of specific BSDT parameters, the confidence level of decisions, and demonstrate that the BSDT’s ROCs and BDPs, as functions of the number of NN disrupted links, have specific features, though rather strange at first glance but consistent with psychophysics experiments (for example, judgment errors in cluttered environments).