TY - JOUR
T1 - An Evidential Extension of the MRII Training Algorithm for Detecting Erroneous MADALINE Responses
AU - Tumuluri, Chaitanya
AU - Varshney, Pramod K.
N1 - Funding Information:
Manuscript received December 22, 1992; revised February 8, 1994 and April 12, 1994. This work was supported in part by the Air Force Office of Scientific Research, Air Force Systems Command, USAF, under Grant F49620-93-1-0122. The authors are with the ECE Department, Syracuse University, Syracuse, NY 13244-1240 USA. IEEE Log Number 9409153.
PY - 1995/7
Y1 - 1995/7
N2 - This paper integrates the evidential reasoning methodology with the parallel distributed learning paradigm of artificial neural networks (ANN). As such, this work presents an algorithm for the detection and, if possible, subsequent correction of the errors in the neuron responses in the output layer of the multiple adaptive linear element (MADALINE) ANN. A geometrical perspective of the MADALINE ANN processing methodology is provided. This perspective is then used to formulate a statistical specification to identify and quantify the sources of uncertainties in the MADALINE processing methodology. A new algorithm, EMRII, is then developed as an extension to the original MRII (MADELINE rule II) algorithm, to formulate support and plausibility measures based on the statistical specification. The support and plausibility measures, thus formulated, are indicative of the degree of confidence of the ANN, in regards to the correctness of its outputs. Based on the support measure, a scheme utilizing two thresholds is proposed to facilitate the interpretation of the support values for error prediction in the ANN responses. Finally, simulation results for the application of the EMRII algorithm in the prediction of erroneous responses in an example problem is presented. These simulation results highlight the error detection capabilities of the EMRII algorithm.
AB - This paper integrates the evidential reasoning methodology with the parallel distributed learning paradigm of artificial neural networks (ANN). As such, this work presents an algorithm for the detection and, if possible, subsequent correction of the errors in the neuron responses in the output layer of the multiple adaptive linear element (MADALINE) ANN. A geometrical perspective of the MADALINE ANN processing methodology is provided. This perspective is then used to formulate a statistical specification to identify and quantify the sources of uncertainties in the MADALINE processing methodology. A new algorithm, EMRII, is then developed as an extension to the original MRII (MADELINE rule II) algorithm, to formulate support and plausibility measures based on the statistical specification. The support and plausibility measures, thus formulated, are indicative of the degree of confidence of the ANN, in regards to the correctness of its outputs. Based on the support measure, a scheme utilizing two thresholds is proposed to facilitate the interpretation of the support values for error prediction in the ANN responses. Finally, simulation results for the application of the EMRII algorithm in the prediction of erroneous responses in an example problem is presented. These simulation results highlight the error detection capabilities of the EMRII algorithm.
UR - http://www.scopus.com/inward/record.url?scp=0029344087&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0029344087&partnerID=8YFLogxK
U2 - 10.1109/72.392250
DO - 10.1109/72.392250
M3 - Article
AN - SCOPUS:0029344087
SN - 1045-9227
VL - 6
SP - 880
EP - 892
JO - IEEE Transactions on Neural Networks
JF - IEEE Transactions on Neural Networks
IS - 4
ER -