Adaptive Tesselation CMAC
OA Version
Citation
Abstract
An ndaptive tessellation variant of the CMAC architecture is introduced. Adaptive tessellation is an error-based scheme for distributing input representations. Simulations show that the new network outperforms the original CMAC at a vnriety of learning tasks, including learning the inverse kinematics of a two-link arm.
Description
License
Copyright 1994 Boston University. Permission to copy without fee all or part of this material is granted provided that: 1. The copies are not made or distributed for direct commercial advantage; 2. the report title, author, document number, and release date appear, and notice is given that copying is by permission of BOSTON UNIVERSITY TRUSTEES. To copy otherwise, or to republish, requires a fee and / or special permission.