Unnamed comments on Open Thread, January 4-10, 2016 - Less Wrong

5 Post author: polymathwannabe 04 January 2016 01:06PM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (430)

You are viewing a single comment's thread. Show more comments above.

Comment author: Viliam 04 January 2016 03:59:29PM 23 points [-]

Lessons from teaching a neural network...

Grandma teaches our baby that a pink toy cat is "meow".
Baby calls the pink cat "meow".
Parents celebrate. (It's her first word!)

Later Barbara notices that the baby also calls another pink toy non-cat "meow".
The celebration stops; the parents are concerned.
Viliam: "We need to teach her that this other pink toy is... uhm... actually, what is this thing? Is that a pig or a pink bear or what? I have no idea. Why do people create such horribly unrealistic toys for the innocent little children?"
Barbara shrugs.
Viliam: "I guess if we don't know, it's okay if the baby doesn't know either. The toys are kinda similar. Let's ignore this, so we neither correct her nor reward her for calling this toy 'meow'."

Barbara: "I noticed that the baby also calls the pink fish 'meow'."
Viliam: "Okay... I think now the problem is obvious... and so is the solution."
Viliam brings a white toy cat and teaches the baby that this toy is also "meow".
Baby initially seems incredulous, but gradually accepts.

A week later, the baby calls every toy and grandma "meow".

Comment author: Unnamed 05 January 2016 09:44:37AM 0 points [-]

Sounds like she hasn't learned shape bias yet.