Title :
A connectionist network for simultaneous perception of multiple categories
Author :
Basak, Jayanta ; Murthy, C.A. ; Chaudhury, Santanu ; Majumder, D. Dutta
Author_Institution :
Nodal Centre for Knowledge Based Computing, ECSU, Calcutta, India
fDate :
30 Aug-3 Sep 1992
Abstract :
A connectionist network is presented for simultaneous perception of multiple categories. These categories provide an adequate explanation of the input features originating from multiple classes. The network optimises an appropriately defined error function for making the inference. A supervised learning algorithm is presented for learning the association between the features and each individual category
Keywords :
inference mechanisms; learning systems; neural nets; connectionist network; error function; inference; input features; learning systems; multiple categories; neural nets; simultaneous perception; supervised learning algorithm; Diseases; Humans; Medical diagnosis; Negative feedback; Neural networks; Output feedback; Pattern classification; Problem-solving; Supervised learning; Uncertainty;
Conference_Titel :
Pattern Recognition, 1992. Vol.II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on
Conference_Location :
The Hague
Print_ISBN :
0-8186-2915-0
DOI :
10.1109/ICPR.1992.201717
