In the days when Sussman was a novice, Minsky once came to him as he sat hacking at the PDP-6. "What are you doing?" asked Minsky. "I am training a randomly wired neural net to play Tic-Tac-Toe," Sussman replied. "Why is the net wired randomly?" asked Minsky. "I do not want it to have any preconceptions of how to play," Sussman said. Minsky then shut his eyes. "Why do you close your eyes?" Sussman asked his teacher. "So that the room will be empty." At that moment, Sussman was enlightened. davew - .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. . FRIAM Applied Complexity Group listserv Zoom Fridays 9:30a-12p Mtn GMT-6 bit.ly/virtualfriam un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com archives: http://friam.471366.n2.nabble.com/ FRIAM-COMIC http://friam-comic.blogspot.com/ |
Meaning, what, exactly?
I wonder why Minsky decided to be vague? Why is Sussman’s desire to avoid engineering a solution not an appropriate concern? Still to this day there is not really a science on how to choose a neural net connectivity. How many random
leave-outs, how many skip-level links, etc. From: Friam <[hidden email]> On Behalf Of
Prof David West In the days when Sussman was a novice, Minsky once came to him as he sat hacking at the PDP-6. "What are you doing?" asked Minsky. "I am training a randomly wired neural net to play Tic-Tac-Toe," Sussman replied. "Why is the net wired randomly?" asked Minsky. "I do not want it to have any preconceptions of how to play," Sussman said. Minsky then shut his eyes. "Why do you close your eyes?"
Sussman asked his teacher. "So that the room will be empty." At that moment, Sussman was enlightened. davew - .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. . FRIAM Applied Complexity Group listserv Zoom Fridays 9:30a-12p Mtn GMT-6 bit.ly/virtualfriam un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com archives: http://friam.471366.n2.nabble.com/ FRIAM-COMIC http://friam-comic.blogspot.com/ |
Minsky was simply illustrating you cannot avoid programming without preconceptions.
Another: -------- A novice was trying to fix a broken Lisp machine by turning the power off and on. Knight (Tom Knight), seeing what the student was doing, spoke sternly: " You cannot fix a machine by just power-cycling it with no understanding of what is going wrong." Knight turned the machine off and on. The machine worked. -------- As a general strategy for fixing things over the phone, this strategy works much of the time. However, in this case, the point would be that the machine was always "working". The joke here is that in those days in most of the Lisp Machines (at least our Symbolics ones) all the boards had at least a few jumper cables, and that no two boards had quite the same jumpers, yet they "worked". Another is that we often turned off the GC and ran them til they ran out of memory, then power cycled. So preconceptions are conserved; sometimes in one machine, sometimes in another. C - .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. . FRIAM Applied Complexity Group listserv Zoom Fridays 9:30a-12p Mtn GMT-6 bit.ly/virtualfriam un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com archives: http://friam.471366.n2.nabble.com/ FRIAM-COMIC http://friam-comic.blogspot.com/ |
Free forum by Nabble | Edit this page |