Science Shown your Koan Wrong!

https://sfari.org/news-and-opinion/toolbox/virtual-brain-suggests-neural-connections-form-randomly

junctions between neurons form randomly and not as the result of chemical signals

"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.

I never liked Minsky much anyway.

how does the brain generate random numbers?

>>2

I loved his silly joke-books. Anyone remember "K-Lines"?

>>3
Perhaps by randomly, they mean it just does what it does with no apparent cause or correlation with anything else?

Here is the formal proof, that Minsky is wrong:
http://www.eecs.berkeley.edu/~brecht/papers/08.rah.rec.nips.pdf

we show that training a shallow architecture by randomly choosing the nonlinearities in the first layer results in a classifier that is not much worse than one constructed by optimally tuning the non-linearities.

How does that falsify the Minsky-Sussman koan? I think in that story Minsky just wanted to tell Sussman that randomly wired doesn't imply absence of preconceptions, just like closing your eyes doesn't imply the emptiness of the room (it could still be empty, or not).

Brain ≠ Mind

>>7
A uniform sample selection would guarantee absence of bias (preconceptions). But Minsky, being a Jew, samples only Jewish opinions, during a statistical survey.

So if you give Minsky a government statistician job, he will survey Jewish population should the government implement mandatory circumcision policy, and then recommends the government to implement the policy based on the fact that %99.9 surveyed were pro mandatory circumcision.

>>9
not even DQN tier...

>>10

Shalom, Hymie!

>>11
Is that you Nikita?

koan

Back to /lounge/, RedCream.

NERDS