[Sussex] partitions and the like ??

Geoffrey Teale tealeg at member.fsf.org
Mon Jan 3 23:03:36 UTC 2005


Steve Dobson wrote:
> I'm sure others will agree that you had already done most of the work.

Ah, the problem with random traversal of a problem space is that you 
need some heuristic functions to indicate which paths are closest to the 
goal states.

Which reminds me of one of my favourite koans:

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.


--
Geoff Teale
Free Software Foundation <tealeg at member.fsf.org>




More information about the Sussex mailing list