121–130 of 188 posts
I met Minsky once in February 1987, at a rally in Las Vegas to protest the Nevada Test Site.. A lot of famous people (Carl Sagan, Barbara Boxer, Tom Downey, Ramsey Clark, Martin Sheen, Kris Kristofferson) were there, but I'd gone to meet Minsky. I had taken along a (quite early) copy of the GNU Emacs manual. The FSF was selling them, but I'd put this one together myself. Running TeX on the texinfo source, converting…
Do you still have it? I'd love to see a picture
Isaac Asimov: "The only people I ever met whose intellects surpassed my own were Carl Sagan and Marvin Minsky."
Isaac Asimov: "The only people I ever met whose intellects surpassed my own were Carl Sagan and Marvin Minsky."
...He also said that he thought McCarthy was an idiot. :)
> True story: in my final essay of my AI module at uni, I disagreed with everything Minsky believed, so my professor, a fan, flunked me.
Earlier quoted context omitted.
"We" certainly do judge, even if that judgement has no practical value. People do act as if it's up for debate. Whenever we decide one death is worthy of it and ignore others, or get into petty arguments if it doesn't appear fast enough, or for the right person. An expectation builds which, if not properly catered to, leads to insult and animosity. And given that it's Hacker News, sometimes suspicion and paranoia. It…
I'd say the solution here is not to end the black bars, but to end the petty disputes by being more civilized in the discussions. Perhaps that's too much to ask, but we should give it a shot.
Earlier quoted context omitted.
From the jargon file [1] [1] http://www.catb.org/jargon/html/koans.html#id3141241
Found this original version copied from this story (original source is a dead link) [1] "So Sussman began working on a program. Not long after, this odd-looking bald guy came over. Sussman figured the guy was going to boot him out, but instead the man sat down, asking, “Hey, what are you doing?” Sussman talked over his program with the man, Marvin Minsky. At one point in the discussion, Sussman told Minsky that he wa…
I had the chance to walk with Marvin Minsky down a hallway once, and I asked him what he thought of Bayesian reasoning. He said that it seemed to him like it was still part of a general trend away from tackling the central problem in AI. I said I didn't think so, but he seemed tired so I didn't try to go into detail. There's an urban legend that I once got into a fistfight with Marvin Minsky, which does about as well…
> We have temporarily misplaced a great mind. See you later, Professor Minsky. This kind of statement gives me great hope, and in particular represents the kind of fundamental mindset change that helps counter many of the painful aphorisms commonly pulled out when someone dies. I find it deeply unfortunate how rarely it applies, but as mentioned elsewhere in the thread, it applies here. Thank you.
Earlier quoted context omitted.
> We have temporarily misplaced a great mind. See you later, Professor Minsky. This kind of statement gives me great hope, and in particular represents the kind of fundamental mindset change that helps counter many of the painful aphorisms commonly pulled out when someone dies. I find it deeply unfortunate how rarely it applies, but as mentioned elsewhere in the thread, it applies here. Thank you.
I think it's more in reference to him being cryo-preserved. According to one of the other comments on this thread.
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…
http://www.newyorker.com/magazine/1981/12/14/a-i
"Because of the random wiring, it had a sort of fail-safe characteristic. If one of the neurons wasn’t working, it wouldn’t make much of a difference—and, with nearly three hundred tubes and the thousands of connections we had soldered, there would usually be something wrong somewhere. In those days, even a radio set with twenty tubes tended to fail a lot. I don’t think we ever debugged our machine completely, but that didn’t matter. By having this crazy random design, it was almost sure to work, no matter how you built it."
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…
It is now several decades later. Do TensorFlow/CNN builders use random initial configurations, or custom designed stuctures?