Simple Artificial Neural Network entirely in assembly language

[@ComputingMongoose]

The code for my simple assembly language artificial neural network is now on github: github.com/ComputingMongoose/AsmANN

[@academicpresentations6062]

Someone is going down a rabbit hole for nerdy people like me and we are very grateful for that

[@ComputingMongoose]

Glad you enjoyed it !

[@iCrimzon]

Ive always made jokes about writing NNs in x64 ASM or COBOL on programming language vids but this guy actually did it. You made my dream come true.

[@ComputingMongoose]

Always happy to make someone's dream come true 😅

[@iCrimzon]

@@ComputingMongoose now im gonna copy your code and put my money where my mouth is, learn to make NNs in asm even if its just twice for fun

[@ComputingMongoose]

@@iCrimzon Sounds great !

[@elementare.]

You're insane, I'll watch your videos from start. Thank u!

[@ComputingMongoose]

I'm glad you enjoyed it. Also, stay tuned for more. I will post in a few days a comparison with Pytorch Lightning for the same small data and will continue building more functionality for my ASM neural network.

[@JoeBurnett]

Wow! This is great! I would also love seeing this adapted in ARM assembly if you’re taking suggestions for future videos.

[@ComputingMongoose]

Suggestions are always welcome! I am also playing with a Pi Pico at the moment, but not in assembly. In the future however I may do some ARM assembly as well.

[@amadzarak7746]

Amazing work brother. Just subbed. Can’t wait to see ur future content and projects

[@ComputingMongoose]

Thanks! Glad to have you on board!

[@aladinmovies]

I am thinking about this (but I cannot program). Your work is incredible, keep it up! Thank you!

[@ComputingMongoose]

Glad you enjoyed it!

[@shreymaru1613]

Crazy idea and efforts to make this 🤯

[@ComputingMongoose]

Glad you enjoyed it! And not really that much effort. I always enjoyed assembly and I'm currently working in AI research, so I was really curious how it compares to have it in ASM vs Python. In a few days I will post a video with the speed comparison of a similar small network implemented in Pytorch Lightning, for the same data and no gpu. So stay tuned for more crazy stuff 😎 🙃

[@RichardLofty]

Test your performance against the same network written in other languages!

[@ComputingMongoose]

I do have a video exactly about this: ASM vs Pytorch Lightning kzbin.info/www/bejne/oGqnkoCYaNh7rdU

[@Abhishekedutain]

Ohh, man i love this really.

[@alexleo4863]

Creating a neural network with bare hands, this is insane

[@ComputingMongoose]

Glad you enjoyed it!

[@ChristopherLePage-o2f]

Thank you for uploading this. I am researching how to write chatbots. This helps a lot. .pytorch is powerful software language... My personal favorite.. Cheers :)

[@ComputingMongoose]

Glad it was helpful!

[@zamplify]

This is insane ❤

[@ComputingMongoose]

Glad you enjoyed it!

[@fernandoadventius7098]

This is AMAZING!

[@ComputingMongoose]

Glad you enjoyed it !

[@fernandoadventius7098]

@@ComputingMongoose : Subscribed. Please keep posting great Assembly Codes with Neurals.

[@ComputingMongoose]

@@fernandoadventius7098 My other assembly videos are also somewhat related. They will later be assembled into a larger ANN allowing loading external data.

[@therobotocracy]

I was thinking about this.

[@ComputingMongoose]

Judging from the comments, views and likes, it seems a lot of people were thinking about this.

[@vanvicka1]

This is God mode 😂❤

[@ComputingMongoose]

🤣🤣🤣 In this case, Welcome to Heaven 😇

[@fhmisml]

somehow youtube brought me here and this is insane, +1 sub

[@ComputingMongoose]

Glad KZbin worked its magic this time !

[@ddmasterdon]

Com'om let us all contrib to the repo to add more layers ⚜

[@ComputingMongoose]

Pull requests are welcome

[@box9283]

YOU MAD LAD! LOVE YOU MAN!

[@corelativ.]

Such a great video , perhaps could you make an explanation how to learn code on your own way ?

[@ComputingMongoose]

Thank you. This is actually the second request for a learning video. I will try to make one, but not in the very near future since it will take me a while to cover the architecture and the basic instructions.

[@kenedi987]

amazing video,

[@ComputingMongoose]

Thank you!

[@leonlysak4927]

you sick bastard I love it

[@ComputingMongoose]

glad you enjoyed it

[@tusharrakhunde9921]

You're amazing 😮

[@felixhex]

Could we use AVX extensions to accelerate our computation?

[@ComputingMongoose]

For larger networks indeed it should be possible to accelerate it with AVX (or other SIMD extensions). I will likely explore this in the future, after adding more complexity to the network.

[@youtubpremiu0008]

i recently came across your channel and it seems you pretty great at dealing things at hardware level i also want to study and know about the computer hardware and but the problem is i didn't have any organized set of resources which make a lot harder to understand things i do have a pretty knowledge about the computers though but still there so many missing puzzles that are yet to fit to fully understand can you help me please.

[@gac5700]

nand2tetris (building a computer from first principles), computer systems a programmer's perspective, operating systems three easy pieces, computer networking a top down approach

[@ComputingMongoose]

I see user @gac5700 already replied with a nice set of resources. I want to add that sometimes it may be easier to start learning using a simpler CPU (either a microcontroller or an older CPU for example). All CPUs have registers, buses, addresses, data, etc. In a simpler one you can play with a reduced set of such registers and instructions. I would recommend Intel 8080 (you can find a bunch of emulators) or Intel 8088 (again a bunch of emulators or even real hardware). 8088 is the basis for modern x86 architectures and the basic instructions are the same (also when a modern CPU turns on it is basically in 8088 mode). On the microcontroller side, you can easily start playing with a Pi Pico or similar and even create some circuits. Pi Pico has a modern ARM-based or RISC-V based CPU (these are different from x86). It all depends what you want to do with what you learn.

[@ComputingMongoose]

Good ones!

[@burnytech]

nice

[@ComputingMongoose]

Thanks

[@notsojharedtroll23]

I was discussing on a Some comments over videos about this and fucking hell. Very cracked

[@ComputingMongoose]

Glad you enjoyed it

[@GizmoJunk]

Is this Giskard; is this you, from the The Engineering Guild? It sure sounds like it's you.

[@ComputingMongoose]

No.

[@Accanfo]

Nuts

[@Sci-fi-Si]

How to make something simple sound very complicated

[@ComputingMongoose]

I guess it all depends on the languages one is familiar with. For someone used to assembly or other languages it's probably more complicated in python....

[@ChungusTheLarge]

Don't send this video to a PM, or you will never be allowed to use TensorFlow again

[@ComputingMongoose]

🤣🤣🤣

[@ALTINSEA1]

Was this faster since its low level languae?

[@ComputingMongoose]

Actually yes. I will upload a video comparing this to Pytorch Lightning in a couple of days, using the same data and no gpu.

[@turnoff7572]

Here before your chammel gets some traction. Would you be willing to make x86 16 or 32bit assembly tutorials for absolute beginners to programming.

[@ComputingMongoose]

I was considering some beginner tutorials (not in the very near future though), but I was thinking about modern 64-bit stuff. Why are you interested in 16 or 32 bit as a beginner? From a job perspective, nowadays almost everything runs in 64-bit. If you want to do some code optimization or write routines for drivers in assembly you are likely working on 64-bit systems. Alternatively, you could learn ARM / RISC-V for things like embedded systems.

[@filipzdravkovic7134]

@@ComputingMongoose What tutorial or course would you recommend to a person who is completely new to assembler ?

[@ComputingMongoose]

@@filipzdravkovic7134 I'm sorry, but I don't have a particular tutorial or resource in mind. My experience was accumulated over many years from many sources and through work. I do hope you will find a good resource.

[@faridfael8826]

You are legend 😂

[@BryanChance]

Hmmm...ok it's go..:-)

[@warzik5910]

1) what

[@MasabHuq]

You monster

[@ComputingMongoose]

😀😎😵‍💫👽