Titlebook: Investigating Explanation-Based Learning; Gerald DeJong Book 1993 Springer Science+Business Media New York 1993 artificial intelligence.kn

coddle

,Case Study 6 — GRASPER: Learning to Manipulate an Uncertain World,The GRASPER system described in this chapter is intended as a first—generation EBL system with explicit approximation capability. First, the general architecture for the system will be described. Next, an example involving planning uncertainty tolerant grasping operations in robotics will be described to illustrate how the approach works.

商品

察覺

Derogate

,A Perspective on Explanation—Based Learning,tional or.machine learning systems [.–.]. The background knowledge is used automatically to construct an explanation of a few training exemplars. The learned concept is generalized directly from this explanation.

樂意

Explanation Generalization in EGGS,hanisms for performing explanation—based learning [.–.]. Prior to the development of these techniques, a number of domain—dependent systems were built which used similar generalization techniques to learn concepts, heuristics, or plans from single examples by analyzing their underlying causal structure [.-.].

bisphosphonate

Recoverable Simplifications and the Intractable Domain Theory Problem, relevant data is enormous. Even in game domains such as chess, the contrast between human and computer approaches is glaringly apparent. Computer chess programs assess potential moves by evaluating millions of possible board positions. Human chess experts evaluate potential moves by analyzing a few key potential avenues of play.

大罵

出汗

Dorsal

憂傷