Abstract
Discovery involves collaboration among many intelligent activities.However, little is known about how and in what form such collaborationoccurs. In this paper, a framework is proposed for autonomous systemsthat learn and discover from their environment. Within this framework,many intelligent activities such as perception, action, exploration,experimentation, learning, problem solving, and new term constructioncan be integrated in a coherent way. The framework is presentedin detail through an implemented system called LIVE, and is evaluatedthrough the performance of LIVE on several discovery tasks. Theconclusion is that autonomous learning from the environment is afeasible approach for integrating the activities involved in a discoveryprocess.
Cite
CITATION STYLE
Shen, W.-M. (1993). Discovery as autonomous learning from the environment. Machine Learning, 12(1–3), 143–165. https://doi.org/10.1007/bf00993064
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.