Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP Path: utzoo!utgpu!water!watnot!watmath!clyde!rutgers!ames!ucbcad!ucbvax!OZ.AI.MIT.EDU!MINSKY From: MINSKY@OZ.AI.MIT.EDU.UUCP Newsgroups: mod.ai Subject: AIList Digest V5 #92 Message-ID: Date: Tue, 31-Mar-87 09:58:00 EST Article-I.D.: MIT-OZ.MINSKY.12290784989.BABYL Posted: Tue Mar 31 09:58:00 1987 Date-Received: Sat, 4-Apr-87 10:35:36 EST References: Sender: daemon@ucbvax.BERKELEY.EDU Distribution: world Organization: The ARPA Internet Lines: 10 Approved: ailist@sri-stripe.arpa The term "demon" comes from Oliver Selfridge, via the paper, "Pandemonium: A Paradigm for Learning", published in Symposium of the mechanization of Thought Processes, November 1858. Selfridge's demons were small feature-detecting agents, whose inputs were linearly weighted sums of other signals, with autonomous hill-climbing learning procedures for determining the weights. Selfridge's demons were arranged in hierarchical networks; typical demons were constantly active - and "shrieking" with intensities proportional to their degrees of arousal; the nonlinear part was that certain "decision demons" would "recognize" which of their inputs was most active.