Technical Report Number
SCL assembles a set of learning modules into a supervised learning system to address the stability-plasticity dilemma. Each learning module acts as a similarity detector for a prototype, and includes prototype resetting (akin to that of ART) to respond to new prototypes. Here (Part I) we report SCL results using back-propagation networks as the learning modules. We used two feature extractors: about 30 energy-based features, and a combination of energy-based and graphical features (about 60). ACL recognized 96% (energy) and 99% (energy/graphical) of test digits, and 91% (energy) and 96% (energy/graphical) of test letters. In the accompanying paper (Part II), we report the results of SCL using fuzzy sets as learning moduels for recognizing handwritten digits.
Kimura, Takayuki Dan; Fuller, Thomas H. Jr.; and Wang, Ce, "Supervised Competitive Learning with Backpropagation Network and Fuzzy Logic" Report Number: WUCS-93-17 (1993). All Computer Science and Engineering Research.