The other day Jabrils was playing a Nintendo game & the AI was so abysmal that he stormed to his computer & make a better one than Nintendo.
Dani, a game developer, recently made a game and decided to train an AI to play it.
A couple of weeks ago I made a video “Making a Game in ONE Day (12 Hours)”, and today I’m trying to teach an A.I to play my game!
Basically I’m gonna use Neural Networks to make the A.I learn to play my game.
This is something I’ve always wanted to do, and I’m really happy I finally got around to do it. Some of the biggest inspirations for this is obviously carykh, Jabrils & Codebullet!
In this edition of Crash Course AI, Jabrils explains how neural networks learn.
Here’s a great explanation of supervised learning from Crash Course AI.
Here’s the first episode of Crash Course AI with Jabrils.
Jabrils developed an app for the 2019 Call for Code global challenge.
You can also submit yours by 7/29 for a chance to win $200,000 USD.
We’re right in the thick of baseball season here in the US, which makes this video on ML particularly timely. Baseball is known for it’s sometimes ridiculous hand signals to relay messages to players in the field. Can AI decode these signals? Spoiler alert: yes.
You have to wonder how long it will be before this technology will be deployed at the major league level, if it hasn’t been already.
Jabrils has an interesting concept here: a Turing Test themed game show.
YouTuber Jabrils shares his history of how he got into machine learning, what inspired him, and about his first machine learning game.
Plus, some cool dance moves during his re-enactment of making his first neural network.