Live data from Hacker News

A.I. Experiments

aiexperiments.withgoogle.com

1–10 of 51 posts

Re: A.I. Experiments

#4
post #3

https://aiexperiments.withgoogle.com/quick-draw.. . this is just too cool. Basically, you draw a picture and see it guess what you are drawing. Worth 2 minutes of your time!

I drew an amorphous square and it correctly guessed it was meant to be a "police car". It has the potential to be fun.

Re: A.I. Experiments

#5
post #3

https://aiexperiments.withgoogle.com/quick-draw.. . this is just too cool. Basically, you draw a picture and see it guess what you are drawing. Worth 2 minutes of your time!

I drew a radio and it said it is a cello. Other than that it is pretty accurate.

Re: A.I. Experiments

#6
These are fun. Be wary of dragging your mouse around on the sequencer thing or the bird call classifier. Makes a hell of a racket.

What I really want in there is the computer-generated music and sample-level speech synthesis they have limited demos of in the WaveNet post:

https://deepmind.com/blog/wavenet-generative-model-raw-audio...

Re: A.I. Experiments

#8
post #3

https://aiexperiments.withgoogle.com/quick-draw.. . this is just too cool. Basically, you draw a picture and see it guess what you are drawing. Worth 2 minutes of your time!

Apparently it's supposed to learn as people supply more things it doesn't recognize? This sounds familiar... [1]

1: http://www.theverge.com/2016/3/24/11297050/tay-microsoft-cha...

Re: A.I. Experiments

#10
It asked me to draw a tree. I drew a palm tree. It said "palm tree" on the bottom, but then said it failed.

I drew the palm tree because I've studied AI and that's a classic AI mistake.

If you go to Hawaii and ask students to draw a tree, almost all of them will draw a palm tree. Ask them to draw a bird and it looks like a parrot (instead of the robin you see typically in the "lower 48").

It's interesting that this seems to suffer from the same selection bias.

Post reply on HN