Adaptive pen user interface with supervised competitive learning
An Adaptive user interface for a pen-based educational application and the related technical difficulties are discussed The Supervised Competitive Learning (SCL) model is proposed as a mechanism for a pen-based adaptive user interface. It offers a solution for one of the fundamental problems of using neural for adaptive user interface; the Grossberg's stability-plasticity dilemma.
KeywordsInput Pattern Handwriting Recognition Adaptive Resonance Theory Adaptive User Interface Prototype Pattern
- Kimura, T.D. “Learning Math with Silicon Paper,” Technical Report WUCS-9211, Department of Computer Science, Washington University in St. Louis, 1992.Google Scholar
- Fuller, Jr., T.H. and T.D. Kimura. “Supervised Competitive Learning,” Journal of Intelligent Material Systems and Structures and Mathematical and Computer Modeling, 5:2 (1994), pp. 232–246.Google Scholar
- Carpenter, G. A. and S. Grossberg. “ART2: Self-Organizing of Stable Category Recognition Codes for Analog Input Patterns,” Applied Optics (1987) pp. 4919–4930.Google Scholar
- Carpenter, G. A. and S. Grossberg. “The ART of Adaptive Pattern Recognition by a Self-Organizing Neural Network,” IEEE Computer 21:3 (1988), pp. 77–88.Google Scholar