On Efficiency of Learning: A Framework and Justification.
Jindřich Bůcha · 2000
. A conceptual framework whose goal is the efficiency of machine learning is proposed and justified. The framework is designed in a broader context, that of problem solver (PS). The design is solved as an integration of all basic cognitive functions and as a software-engineering problem. Many (one hundred) requirements imposed on PS are considered. The most important are the object-oriented nature of the PS environment, reflexivity of PS, and central role of tool and shifted border. 1 INTRODUCTION In the paper, a framework for machine learning is proposed. It is a new framework 2 , even if it is "99%-based" on known concepts, based on their integration. There are a lot of them. They are unified in one super-principle (see later). The sophisticated robots on RoboCup-99 did not demonstrate a very intelligent game. This was not because they were not able to form teams of autonomous robots, demonstrate multi-source fusion of perception, and use multi-agent game theory. I contrast thes...