Title :
Developmental learning of memory-based perceptual models
Author :
Ivanov, Yuri A. ; Blumberg, Bruce M.
Author_Institution :
Fundamental Res. Labs, Honda R&D Americas, Boston, MA, USA
Abstract :
This paper reviews an online learning algorithm for incremental learning of memory-based utterance models. The simple core algorithm is augmented with a strategy for selecting the compression set-a subset of the input data that possesses some optimality characteristics. These sets are again found incrementally. Several strategies are formulated and empirically compared on three standard data sets. The algorithm is used as a perceptual learning component of an adaptive autonomous agent.
Keywords :
learning (artificial intelligence); optimisation; pattern classification; compression set selection; core algorithm; developmental learning; incremental learning; memory-based perceptual models; memory-based utterance models; online learning algorithm; Animals; Autonomous agents; Grounding; Kernel; Laboratories; Machinery; Pattern recognition; Research and development; Support vector machine classification; Support vector machines;
Conference_Titel :
Development and Learning, 2002. Proceedings. The 2nd International Conference on
Print_ISBN :
0-7695-1459-6
DOI :
10.1109/DEVLRN.2002.1011833
