A.I. Experiments: Quick, Draw!

Views:597483|Rating:4.70|View Time:1:41Minutes|Likes:1379|Dislikes:88
Check out to learn more.

This is a game built with machine learning. You draw, and a neural network tries to guess what you’re drawing. Of course, it doesn’t always work. But the more you play with it, the more it will learn. It’s just one example of how you can use machine learning in fun ways.

Built by Jonas Jongejan, Henry Rowley, Takashi Kawashima, Jongmin Kim, with friends at Google Creative Lab and Data Arts Team.

hi i'm yonis I am Henry quick draw is a game a few of us at Google made the droll and the computer uses machine learning to guess what you're drawing I see square or suitcase or canoe oh I know it's shoe it's an experiment that uses some of the same technologies that helps Google Translate recognize your handwriting to understand handwriting our drawings you don't just look at what the person drew you look at how they actually drew it which strokes did they make first which direction did they drop on them train the computer on millions of characters from hundreds of languages and over time it learns with you wrote look or whether you're wrote book training is a big part of how the computer can get your drawings correctly as people it's easy for us to look at these three drawings and know they're all cats but your computer they're very different one is just a head one has several body and one is just facial features so get the computers on a stand to have to shoot a lot of cat doodles and then it starts to see patterns like that almost all doodles of cat's head pointy ears small nose and whiskers cause it doesn't always work that's because it's only seen a few thousand doodles but the more you play with it the more it will learn the better it will get it guessing oh I know it's cat we put it on the web for anyone to play with we hope you inspires are the people to think about fun ways to use machine learning you can play it at Kiko /ai experiments you

49 thoughts on “A.I. Experiments: Quick, Draw!

  1. I don't know how to send suggestions but it should be more careful with translations, a for example it traslated bucket as "cubo" but "cubo" also means cube so sometimes you don't really know what it wants.

  2. Question, does the AI know in advance a limited amount of possibilities? Because why does it gues 'police car' (instead of car) when I haven't even started drawing the police specific parts of a car.
    So that is very strange, the AI should guess 'car' first.

  3. The translate is inaccurate. It requires me to draw a 扇子(that generate wind by swaying a piece of paper or something), but with other's 電扇(that generate wind with election) pictures

  4. This game is great! I could use it in my computer art class to give students a short fun activity. It would be even better if people could challenge each other to draw the same prompts within the 20 second period, and first one wins.

  5. My one complaint is that it's very hard to do this with a mouse on your laptop vs using your finger or a stylus on a mobile device. Other than that it's pretty fun.

  6. YOU GUYS ARE NO MORE THAN A COUPLE OF PATHETIC 3 YR OLDS, WHO DON`T KNOW HOW TO DRAW CORRECTLY!!!!!!!!!!!!! I played your game, and when I looked at pictures of what I was expected to draw of a guitar, and IT LOOKED LIKE A TODDLER DID THAT PICTURE!!!!!!!!!!!!

    | /|
    | / |
    | __ /__|_


  7. One of it's problems it that is making guesses from other doodles, but not from how we truly see things, now since most people don't draw in perspective, if you start drawing objects in perspective the systems is unable to recognize some of the objects.

Leave a Reply

Your email address will not be published. Required fields are marked *