Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP Path: utzoo!watmath!clyde!floyd!harpo!seismo!hao!hplabs!sri-unix!WELD%MIT-OZ@MIT-MC.ARPA From: WELD%MIT-OZ@MIT-MC.ARPA Newsgroups: net.ai Subject: Procedural Learning (Boston) Message-ID: <17525@sri-arpa.UUCP> Date: Mon, 12-Mar-84 13:39:00 EST Article-I.D.: sri-arpa.17525 Posted: Mon Mar 12 13:39:00 1984 Date-Received: Fri, 16-Mar-84 02:52:33 EST Lines: 23 From: "Daniel S. Weld"[Forward from the MIT bboard by SASW@MIT-MC.] Wednesday, March 14 4:00pm 8th floor playroom Acquisition of Procedural Knowledge from Examples P. M. Andreae I will describe NODDY - a system that acquires procedures from examples. NODDY is a variation of concept learning in which the concepts to be learned are procedures in the form of simple robot programs. The procedures are acquired by generalising examples obtained by leading a robot through a sequence of steps. Three distinct types of generalisation are involved: structure generalisation (eg. loops and branches), event generalisation (eg. the branching conditions), and function induction. I will also discuss two principles that arise out of, and are illustrated by, NODDY. I claim that these principles have application, not only to procedure acquisition, but also to any system that does partial matching and/or generalisation of any kind.