ud188の至言

Lesson 7 #9

It's not so complicated after all, isn't it?
Now you may be thinking, wait a minute, this looks too arbitrary.
Why use tanh sometimes and sigmoid other times?
Why multiply sometimes and add other times, and other times apply a more complicated linear function?
You can probably think of different architectures that make more sense or that are simpler, and you are absolutely right.
And as many things in machine learning, the reason why it is like this is because it works.

わかる。 Done is better than perfect. ってわけでもないけど、完璧に辻褄が合ってから使うよりも、とにかくうまくいくものを使って知見を貯めていくことも実世界では重要なこともあるのかもしれない。Done is better than perfect - らんだむな記憶の頃にも引用したなぁ。そう言えば、この言葉の逸話も Facebook だが、PyTorch も Facebook だな。