Erasmus, FCD
Posts: 6349 Joined: June 2007
|
from metaprogramming and dna
fresh meat (gi-stu wa-tali ha)
Quote | In your analysis of your recent IEEE paper, you suggest that the environment contains no inherent information to select towards, and thus cannot effectively be used as the endpoint of a search algorithm. To this, I would like to respond with the following quote, taken from Wikipedia, describing an interaction between Gerald Sussman and Marvin Minsky of the MIT AI lab:
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.
What I actually said was, “If you wire it randomly, it will still have preconceptions of how to play. But you just won’t know what those preconceptions are.” –Marvin Minsky |
the socks at UD are so much more interesting than the regular commenters. i appreciated the zen, bunny! thanks!
-------------- You're obviously illiterate as hell. Peach, bro.-FtK
Finding something hard to believe based on the evidence, is science.-JoeG
the odds of getting some loathsome taint are low-- Gordon E Mullings Manjack Heights Montserrat
I work on molecular systems with pathway charts and such.-Giggles
|