Publication Type

Conference Proceeding Article

Publication Date

6-2007

Abstract

Machine learning, a cornerstone of intelligent systems, has typically been studied in the context of specific tasks, including clustering (unsupervised learning), classification (supervised learning), and control (reinforcement learning). This paper presents a learning architecture within which a universal adaptation mechanism unifies a rich set of traditionally distinct learning paradigms, including learning by matching, learning by association, learning by instruction, and learning by reinforcement. In accordance with the notion of embodied intelligence, such a learning theory provides a computational account of how an autonomous agent may acquire the knowledge of its environment in a real-time, incremental, and continuous manner. Through a case study on a minefield navigation domain, we illustrate the efficacy of the proposed model, the learning paradigms encompassed, and the various types of knowledge learned.

Keywords

Choice Function, Autonomous Vehicle, Adaptive Resonance Theory, Neural Architecture, Category Node

Discipline

Databases and Information Systems | Numerical Analysis and Computation

Research Areas

Data Science and Engineering

Publication

Advances in Neural Networks: International Symposium on Neural Networks (ISNN) 2007: Nanjing, June 3-7, Proceedings

Volume

4491

Issue

PART 1

First Page

1094

Last Page

1103

ISBN

9783540723837

Identifier

10.1007/978-3-540-72383-7_128

Publisher

Springer

City or Country

Berlin

Additional URL

https://doi.org/10.1007/978-3-540-72383-7_128

Share

COinS