LESSWRONG
LW

767
JakobHeiss
0010
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No wikitag contributions to display.
DSLT 2. Why Neural Networks obey Occam's Razor
JakobHeiss16d10

In Footnote 1, I would have expected q(y|x)=N(x2,0.152) instead of q(y|x)=N(x2,1), since y=x2+ε where ε∼N(0,0.152). If the standard deviation of the noise is 0.15, then also the log-likelihood function in Footnote 3 should be adjusted.

Reply
No posts to display.