Title :
An ART2-TPM neural network for automatic pattern classification
Author :
Fujita, Masahiro ; Bavarian, Behnam
Author_Institution :
Dept. of Electr. & Comput. Eng., California Univ., Irvine, CA, USA
Abstract :
Presents a novel two-layer neural network based on the adaptive resonance theory (ART2) network for continuous variables in which the bottom-up long-term memory (LTM) and the top-down LTM adaptations use the self-organizing topology preserving mapping (TPM) learning rule. This topology is developed in the context of an extended Neocognitron for automatic pattern clustering from raw two-dimensional image inputs to a finite number of classes. The complete ART2-TPM algorithm is presented and an illustrative example for automatic recognition of line orientation is given. The performance of the network is compared to that of the winner-take-all network
Keywords :
adaptive systems; computerised pattern recognition; learning systems; neural nets; resonance; self-adjusting systems; topology; ART2-TPM neural network; Neocognitron; adaptive resonance theory; automatic pattern classification; learning rule; line orientation; long-term memory; pattern clustering; performance; self-organizing topology preserving mapping; two-dimensional image inputs; two-layer neural network; winner-take-all network; Clustering algorithms; Computer vision; Network topology; Neural networks; Neurons; Pattern classification; Pattern clustering; Pattern recognition; Resonance; Robustness;
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
DOI :
10.1109/IJCNN.1991.155380
