Game Emulation via Neural Network
I made a playable Pokémon overworld. It looks (mostly) like a normal video game, and you can try it in your web browser here: Although this looks like a video game, I did not write any game code. This program is actually a neural network mimicking a video game. A human could run through these instructions to transform input into output: Instructions The instructions above are a program, written in natural language, for humans. Some in-between steps are unspecified (how do you add two numbers? what even is a number, anyway?) but it’s okay, because humans have a lot of background knowledge that they can use to fill in the gaps. A computer could run through these instructions to transform input into output: This is also a program (the same one as before), now written in a programming language. Computers can directly translate programming languages into computer languages. This means, if we write our program in a programming language, no human ever needs to run through the program. We can
Game Emulation via Neural Network Game Emulation via Neural Network 05 September 2022 I made a playable Pokémon overworld. It looks (mostly) like a normal video game, and you can try it in your web browser here : Although this looks like a video game, I did not write any game code. This program is actually a neural network mimicking a video game. Program? Game? Neural network? Programs: sequences of instructions that transform input→output A human could run through these instructions to transform input into output: Instructions Take two input numbers Sum the numbers Halve that to get you
Explore this link on the map →saved by
related reading
- World Emulation via Neural Networkmadebyoll.in
- A Recipe for Training Neural Networkskarpathy.github.io
- Neural networks and deep learningneuralnetworksanddeeplearning.com
- A Recipe for Training Neural Networkskarpathy.github.io
- What Is ChatGPT Doing … and Why Does It Work?-Stephen Wolfram Writingswritings.stephenwolfram.com
- Software 2.0. I sometimes see people refer to neural… | by Andrej Karpathy | Mediumkarpathy.medium.com
- The Unreasonable Effectiveness of Recurrent Neural Networkskarpathy.github.io
- Andrej Karpathy — AGI is still a decade awaydwarkesh.com
- The World Inside Neural Networksgoodfire.ai
- Jane Street Blog - Can you reverse engineer our neural network?blog.janestreet.com
- Machine Learning, Kolmogorov Complexity, and Squishy Bunniestheorangeduck.com
- Deep learning as program synthesis — LessWronglesswrong.com