We propose a Hybrid System for dynamic environments, where a “Multiple Neural Networks” system works with Bayes Rule to solve a face recognition problem. One or more neural nets may no longer be able to properly operate, due to partial changes in some of the characteristics of the individuals. For this purpose, we assume that each expert network has a reliability factor that can be dynamically re-evaluated on the ground of the global recognition operated by the overall group. Since the net’s degree of reliability is defined as the probability that the net is giving the desired output, in case of conflicts between the outputs of the various nets the re-evaluation of their degrees of reliability can be simply performed on the basis of the Bayes Rule. The new vector of reliability will be used to establish who is the conflict winner, making the final choice (the name of subject). Moreover the network disagreed with the group and specialized to recognize the changed characteristic of the subject will be retrained and then forced to correctly recognize the subject. Then the system is subjected to continuous learning.
A Continuous Learning in a Changing Environment / Dragoni, Aldo Franco; Vallesi, Germano; Baldassarri, Paola. - STAMPA. - 6979:(2011), pp. 79-88. (Intervento presentato al convegno ICIAP 2011 Image Analysis and Processing - 16th International Conference tenutosi a Ravenna nel September 14-16, 2011) [10.1007/978-3-642-24088-1_9].
A Continuous Learning in a Changing Environment
DRAGONI, Aldo Franco;VALLESI, GERMANO;BALDASSARRI, Paola
2011-01-01
Abstract
We propose a Hybrid System for dynamic environments, where a “Multiple Neural Networks” system works with Bayes Rule to solve a face recognition problem. One or more neural nets may no longer be able to properly operate, due to partial changes in some of the characteristics of the individuals. For this purpose, we assume that each expert network has a reliability factor that can be dynamically re-evaluated on the ground of the global recognition operated by the overall group. Since the net’s degree of reliability is defined as the probability that the net is giving the desired output, in case of conflicts between the outputs of the various nets the re-evaluation of their degrees of reliability can be simply performed on the basis of the Bayes Rule. The new vector of reliability will be used to establish who is the conflict winner, making the final choice (the name of subject). Moreover the network disagreed with the group and specialized to recognize the changed characteristic of the subject will be retrained and then forced to correctly recognize the subject. Then the system is subjected to continuous learning.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
