To try everything Brilliant has to offer-free-for a full 30 days, visit brilliant.org/mattbatwings You’ll also get 20% off an annual premium subscription.

@kraralmosawi7843

23 күн бұрын

ok man we got to address your genius 💀😭🙏

@maxtres764

23 күн бұрын

"Why should we try brilliant if we have you?"-me

@YSCU261

23 күн бұрын

i mean, neural networks, brilliant, it's all connected

@DieNow

22 күн бұрын

Did you use a cnn to make the mnist image reduced and input the weights in a feed forward neural network?

@gameingroom5829

22 күн бұрын

Thanks I love brilliant

if you guys think this is insane, it took this guy like 2 weeks to make this all start to finish this man is a MACHINE

@UsedObsidian

22 күн бұрын

lol

@imsaturncat

22 күн бұрын

cwaftymwastewman:3

@Cleacat

22 күн бұрын

Crazy 🎉

@thesoupbird

22 күн бұрын

im sorry WHAT

@marcusthegamer348

22 күн бұрын

@@imsaturncat Ew

ChatGPT playing minecraft: ❌️ Minecraft running ChatGPT: ✅️

@alibrahym

22 күн бұрын

Yeah bro they'll make a server, represent the internet, someone will then recreate chatgpt with redstone make it learn alot and people would be able to use it, but the problem is redstone is very slow, so they have to speed up the time so much, that it even responses in a "ok" time.

@Centorym

22 күн бұрын

Someone NEEDS to make a chat GPT in minecraft, I Don't care if it uses command blocks, it would be so cool!

@tung-hsinliu861

22 күн бұрын

@@Centorym The GPT language models are so huge that, if we convert the whole model into redstone, the scale of the redstone machine will be so large that it will not even fit within render distance! For comparison chatGPT model size is somewhere about 10 million~10 billion times larger than the number-recognitoin model. Yeah I think command blocks is the only way to go, but even that the amount of command blocks would be monumental! And the labor of copying the entire model by hand... I think the conversion process has to be automated to be feasible

@Ari_Fudu

21 күн бұрын

@@tung-hsinliu861 then we must settle for a very barebones version that has predetermined responses - although that'll be more of a magic 8ball ngl

@crispinotechgaming

21 күн бұрын

​@@Ari_Fudubut then it's not a neural network

the ONLY person on youtube that managed to explain neural networks in seconds, it took me days of research to understand them, be able to make and explain them

I will likely never fully understand these videos, but man are they impressive 👏 Incredible work! My brain is fried

@Centorym

22 күн бұрын

ive never seen people not reply to a famous youtuber lol

@Flupus

14 күн бұрын

Hi knarfy

@Flupus

14 күн бұрын

Are you gonna be doing "Breaking a neural network with your dumb ideas"?

@ThatGuyNyan

9 күн бұрын

Fried brain 🤤

@Centorym

9 күн бұрын

@@ThatGuyNyan run knarfy RUN before this guy makes a 3 course meal from you

This was 100% a brilliant partnership

@bummbumm6

23 күн бұрын

It was 💀

@muslimgamerrr9479

22 күн бұрын

😂

@bmmyes

22 күн бұрын

you were right !!

@That1CelloGuy

22 күн бұрын

bad pun (·n·)-p

@PixieNixie5

22 күн бұрын

LMAO

We’re getting to the point where pretty soon someone is gonna recreate the nes in minecraft, or make doom in minecraft, im betting that within 10 years someone will get either doom or super Mario bros or the legend of Zelda running just off redstone

@thisflyingpotato4227

23 күн бұрын

Idk about other games but doom already exist, someone ran it on his redstone computer (I believe it was called IRIS) I'll get back and edit this comment with the code of the video (edit) _SvLXy74Jr4 Also I have no idea if this has been done before

@frkieran

23 күн бұрын

such an original comment

@proceduralism376

22 күн бұрын

Modpunchtree already ran doom on his cpu iris you can look up the video

@feeries8208

22 күн бұрын

@@proceduralism376 yeah and its only 28~32s for each frame

@adryanlucas096

22 күн бұрын

A NES Emulator in minecraft would be CRAZY

We got real AI in Minecraft before GTA 6

@krinodagamer6313

15 күн бұрын

Diabolical

@goldfishglory

14 күн бұрын

😭😭WE ONLY HAVE A COUPLE YEARS TO MAKE THESE JOKES; EVERYTHING WILL STOP BEING IMPRESSIVE SINCE ITS AFTER GTA 6

@_sandy_

14 күн бұрын

i came here looking for this comment LMFAO

@NolanHOfficial

12 күн бұрын

​@@goldfishglorywe got gta 6 before gta 7 - some guy in 2093

@goldfishglory

12 күн бұрын

@@NolanHOfficial true

Bro, people out there creating neural networks in Minecraft, and I'm struggeling opening a chocalate bar while watchin them

@someone-jjj

8 күн бұрын

Bruh

I’m struggling on a 2x2 this dudes making a Neural Network.

@MrFiveHimself

22 күн бұрын

dont worry dude! it just takes time! You should watch his logical redstone reloaded series. (both new and old). they’re really helpful in understanding how computational redstone works. After that, just try to make an ALU. Its an amazing starting goal and once you’ve made your own, you can confidently say you’re proficient. I wish you luck on your journey

@takyc7883

22 күн бұрын

its 4

@Asheetanshu

22 күн бұрын

​@@takyc7883he is talking about door

@MrFiveHimself

22 күн бұрын

@@takyc7883 god damnit i laughed way too hard at that

@nynvib276

21 күн бұрын

​@@MrFiveHimself That's assuming the commenter is not on bedrock.

my brother in christ, IT TOOK ME TWO MONTHS TO MAKE A NETWORK FROM SCRATCH THAT SOVLED THE MNIST DATASET IN PYTHON AND YOU DID IT IN REDSTONE IN 2 WEEKS, i applaude you, you redstone genius

@WoolyCow

22 күн бұрын

lol there is a video i love of some bloke just writing it in like half an hour :> watching it is great way to lose confidence in your abilities

@GustvandeWal

22 күн бұрын

​@@WoolyCow Link?

@WoolyCow

22 күн бұрын

@@GustvandeWal yt doesn't play nice with links, but its called "Building a neural network FROM SCRATCH (no Tensorflow/Pytorch, just numpy & math)"

@GustvandeWal

22 күн бұрын

@@WoolyCow Thx! (Most copy the part after /watch?v= 🙂)

@WoolyCow

22 күн бұрын

@@GustvandeWal oh lol i shouldve thought of that! thanks for the tip :D

I just did a machine learning course last semester, and your 2 minute explanation for an MLP network was way easier to understand than our textbooks chapter that covered it. This entire build is insane, amazing work!

We got AI in Minecraft before GTA 6

You solved a number of difficult problems elegantly, but your amazing ability to communicate those ideas both visually and with narrative ease really stands out. Fantastic piece of content my dude.

The internet is such a cool place, imagine having a degree and choosing it to build real video games and software into minecraft and share it for a job, instead of actually building the video games and software, and making a living from that. The internet is so cool.

@Louis13XIII

22 күн бұрын

Gaming companies are so scummy and exploitative that honestly that's ain't really a bad deal after all

@VortexFlickens

20 күн бұрын

A forum for all ppl from stupid kids to Elon Musk

@watema3381

18 күн бұрын

@@VortexFlickens Not much of a flattering comparison for stupid kids don't ya think?

@Esiv0_

17 күн бұрын

@@VortexFlickens you said stupid kids twice

@Meyer-gp7nq

17 күн бұрын

Wow look at the stupid kids hating on Elon cause he’s successful. Someone made a joke, cope

mattbatwings in 1 year: I Made a Technological Singularity with just Redstone!

Your transcript for college, internships, and future jobs in computer science is gonna be so stacked

In 16-bit logic, you can replace division by 15 by a multiplication by -30583 (32 bit result), three shifts, and two addition operations. You can easily figure this out by compiling a function that returns its 16-bit argument divided by 15 on clang with -O2, and what's efficient to do on silicon fabric (integers over floats, and multiplication over division) is almost always efficient in minecraft too. As for softmax, in 2021, researchers at nvidia created a hardware-efficient softmax replacement called "softermax" that is realistically implementable in minecraft. I'm not a minecraft expert, but I love seeing hardware implementations of functions, and minecraft is no exception.

@law1337

8 күн бұрын

Just because a function is hardware-efficient doesn't necessarily mean it can be easily or efficiently implemented in Minecraft, but it's an interesting point.

@LtDan-fy7lc

5 күн бұрын

@@law1337 "what's efficient to do on silicon ... is almost always efficient in Minecraft too." Java: *raises eyebrow*

14:19 Exponentiation is pretty simple, just convert the exponent to a binary number, then for each bit that is turned on you add the corresponding exponent, and to get the list of corresponding exponents you just start with the number you're raising to the power of the exponent and multiply by two each step. Here's an example, if you have 5^7 then it will convert 7 to binary which is 111 then it will multiply 5, 25, and 625 to get 78,125 which is the correct answer.

@skaleee1207

22 күн бұрын

Also known as Square-And-Multiply algorithm

@flameofthephoenix8395

22 күн бұрын

@@skaleee1207 Nice! I didn't know its official name. Originally, I thought I was the first person to come up with it, I remember being quite proud of it, later on I learned that it already existed, but I didn't know the name until now! That name is a lot simpler than my explanation and will allow people to find more information on it too, thanks!

@sebastiangrau8409

22 күн бұрын

This is an exponential with eulers number. Any output would be irrational and very messy. I understand why he would avoid this.

@antarctic214

22 күн бұрын

You could do it with base 2 (or 4), its just changing the "temperature". In that case exponentiation is trivial (bitshift). But you still have to do division.

@Rudxain

22 күн бұрын

That's like shift-and-add but for exp instead of mul

These projects of your are insane and the fact you choose a project AND actually push yourself to do it is super admirable

This is such a good demonstration that every hard problem is just a ton of smaller easier problems.

offtopic but recently started second semester on my computer science in college and was like "omg it's mattbatwings thing" the whole lecture because i already learned most of the stuff they were talking about from you 💀

It’s always a good day when a mattbatwings Video is on my recommended

@CubeXC

22 күн бұрын

Brp you could not get recommended this before premiere

@user-yp6gm2wi9d

22 күн бұрын

Same

@pauliesnug

22 күн бұрын

@@CubeXC you can. before a premire starts, it can be recommended

i'm amazed how well explained everything in this video is! keep on rocking

I was trying to come up with a project to add to my resume and you just simplified me to focus on ML. Thank you! :)

At this rate in 5 years I'm going to see a video on my homepage from mattbatswings where he ports the entire Linux kernel into Minecraft

@kaz49

9 күн бұрын

Well, they do say that Linux runs on just about anything

Actually you only need to be continuous for training, for deployment you can drastically decrease the precision Without losing accuracy, if you do it right There's a paper where they reduce it all the way to one bit per neuron, which is a perfect fit for minecraft (And I'm pretty sure also to 4 bits, which would fit signal strength applications)

@user-yi8uz2ph1y

22 күн бұрын

quantization baby

@MilkGlue-xg5vj

22 күн бұрын

​​@@user-yi8uz2ph1y Imagine getting a binary quantization good at mnist lol

@whatisrokosbasilisk80

22 күн бұрын

Even for training, you can use quantization-aware or non-differentiable methods and meet parity on inference during training.

@MilkGlue-xg5vj

22 күн бұрын

@@whatisrokosbasilisk80 That's what I'm talking about

@MrSonny6155

20 күн бұрын

I'm guessing this is the BNN paper by Courbariaux et al. from 2016? I'm skimming through the claims and it's insane what quantization can theoretically do.

This guy in 2030: Building robots to colonize all solar system planets with just redstone!

This is absolutely insane, keep up the good work!

The first thing that comes to mind is a recent cutting edge implementation of QAT (quantization aware training) called Bitnet 1.58; it operates on different principles than a standard MLP. It replaces the Matrix multiplication with binary operators (addition, subtraction, or no-ops), so it's fast in inference deployment and cheap in that you can sort of fit a single "unit" of weights into 1.58 bits (though it's easier to just do it as a 2bit implementation with one state unused). It'd probably be way faster in a Minecraft context as one of the biggest disadvantages in IRL deployment, that you need custom hardware to take full advantage of the speed improvements, isn't really a disadvantage in a bespoke system. Anyway, the biggest difference is in the training process; it's trained at Int8 or FP8 (if memory serves, it's been a little while), and is then downscaled to the 1.58bit representation, but the information lost in that conversion to ternary values is preserved in a weight reconstruction matrix, basically. The end goal is that the network is made aware that it will be converted to a ternary representation. Hence, "quantization *aware* training", so you might be able to preserve more of the accuracy of the floating point model than you thought. Strictly speaking, the full bitnet implementation is a Transformer network, but it should still apply to raw MLPs given that they started with the FFN (essentially an MLP placed inside a more complex network with self attention and a language head).

I never thought a Minecraft video will teach me neural network better than my teacher, thanks for the upload

The way you explained all of those deep learning terms in simple words is just marvelous!

You just reinvented the integer quantization! Nice job🎉

Brother. I spent a while learning how to make neural networks as a school project, and just doing this from scratch, in redstone is absloutely astonishing. Legend, Mattbat.

That's incredible! Combining neural networks with Minecraft is pure genius. Keep up the amazing work!

Amazing project, congrats. Note: instead of multiplying the weights by 100, you can perform post-training int8 quantization to maintain most of the original accuracy.

I remember dabbling a bit in neural networks years ago and also went with integers instead of floating point, it was just 5x easier to code in the ancient software I was using on a school PC... Very nice redstone.

Nice i also thought at first that your going to train the model in Minecraft but it seems that if its going to happen its going to be a whole other story

@dumblr

22 күн бұрын

wait 2 more weeks lol

Okay, this just looks bonkers insane. Awesome work.

This taught me about implementing neural networks better than a lot of learning resources I've watched. Good work

Now please make a calculator where you can draw the numbers yourself (using a neural network and calculator) that would be awesome

Ok, now make an AI assisted shape drawing tool for your paint program. e.g. draw a bad square, it draws a good square with the same width and height. draw an ugly number, it fixes it by converting it to the closest possible number with correct dimensions.

@SuitedGhost

22 күн бұрын

that sounds like pure hell I love it

@alluseri

22 күн бұрын

nah

@NoVIcE_Source

17 күн бұрын

@@alluseri i like how google translate assertively translates this to "Now"

dude! seriously, from the bottom of my heart, you deserve sooooo much more recognition! thank you for this fantastic content

This was so cool man. Great job!

1 step closer to google in minecraft

@sillentkillerff9520

Күн бұрын

There is a mod that uses block's as a screen and it connects to Google's url so thechnicly you can wach KZread in Minecraft

Amazing I hope you mention the first guy who did a neural network thing in minecraft, recognising numbers Edit: he did

@ThiaGamesBR

21 күн бұрын

Feels good to comment before watching the video...

@two697

21 күн бұрын

Why would you comment this before watching the video. He mentioned the other guy very early on in the video

@doctoroppa7991

14 күн бұрын

Twitter rot

Great work! You helped me gain a better understanding of the weights. I don’t know why i was having a hard time grasping how the weights worked. Thank you

That’s a marvelous creation to be able to feature on your portfolios.

Bro is bout to build a quantum computer in Minecraft… 💀

respect for the sponsor's dish at the end of the episode

Congratulations, that's so cool! I used to do a lot of redstone back then, so I love seeing people pushing the limits further and further with it :)

This is amazing bro. Great job!

Wow, that's actually crazy, good on you!

Congrats, you passed your PhD thesis.

massive kudos dude, seriously impressive!!!

Dude your project just made me fully understand MLPs and neural networks thank you.

I just started the first few seconds of the video... the Minecraft soundtrack remix is awesome! Gives you a liiitle bit of the nostalgia of the original soundtrack but it feels so cool

WHAT THIS IS THE VIDEO I’VE BEEN WAITING FOR OMGGGG

I'm always happy to see what wizardry you come up with. Keep being awesome man!

This was such an entertaining video yet i still understood what you were talking about. This was amazing!

This is great work! I never thought we would have machine learning with just Redstone.

@bintangramadan3217

23 күн бұрын

There's a guys who made this 1 year ago lol in minecraft

@The.Sponge

23 күн бұрын

@@bintangramadan3217 Yeah but Mattbatwings is aware of that so maybe there will be something new?

@CubeXC

22 күн бұрын

You could npt have seen it yet, stop saying stuff just to get like. It was before premiere

@mineq4967

22 күн бұрын

its not machine learning, he just pasted the weights and biases into the neural network, not making it learn itself like a machine learning algorithm would

@Louis13XIII

22 күн бұрын

@@mineq4967 yeah that's a bit deceptive tbh

This is honestly incredible. I wish this was around when I was studying these concepts, would have helped me understand back propagation and softmax so much quicker

yooooo this is such a big inspiration since for a year or two now ive been working on and off on an AI that speedruns minecraft and i kinda stopped working on it for awhile but i think i might go back to it bc of this! this video brought it all back

Dude its sick and u are on next level , this one got u a subscriber. Keep going!

Can't say enough about how great it is that you showed prior work from others in the community before digging in to your version. That's what we want to see in the community ❤

at this point bro is gonna make hooman brain in redstone dang good job

@ziphy_6471

20 күн бұрын

Cringe

@ALPRNX422

20 күн бұрын

@@ziphy_6471 omg its linus no way 🔥🔥🔥

@ziphy_6471

20 күн бұрын

@@ALPRNX422 I have several children in my basement

@ALPRNX422

20 күн бұрын

@@ziphy_6471 cool

@ziphy_6471

20 күн бұрын

@@ALPRNX422 Will you be my next OwO UwU * turns up bulge *

Man, that looks so fun. Congratulations.

bro what you are a genuine genius. I do not mean this non-literally, you are a genius

We are getting AI in minecraft before GTA VI comes out 💀💀

NO DONT TAKE OUR REDSTONE ENGINEERS JOBS

This is really good bro for visualising how computers work deep down in their tiny chips. Like ur essentially blowing up a cpu to its full size and literally WALKING thru the details and wiring. U can be a goated CS major bro, u have so much f**ING talent bro. How old are you dude? Did you do UNI, or are you currently doing uni? Like bro, go do a CS major or smth, you could make a shit ton of money from just research and development. U got like bottomless talent levels bro

This video was awesome!! It taught me the basics of machine learning but related it all to Minecraft. The perfect combo!

How did u get around the network being bad at actual digit recognition, due to the MNIST data set all being perfectly centered?

@ferguspick6845

15 күн бұрын

A simple MLP can learn a pretty good representation already for this dataset, but one easy approach would be to transform the input images (e.g. skew, rotate) and add these as additional training samples, this makes the learned representations even more robust :)

@InsertName404

15 күн бұрын

@@ferguspick6845 tysm

Wait what!???? Please tell me that this is just uploading the model into redstone and not all complex things like backpropagation to train the NN inside Minecraft...

@FriedMonkey362

23 күн бұрын

For simple nural networks you dont really need backpropagation, you can just randomize the values until it gets better, itll take longer to train and wont be as efficient but its way easier to do

@bintangramadan3217

23 күн бұрын

Bro there's a guy from Chinese who made neural Network in mine5 1 year ago lol

@Abcdef0101_

23 күн бұрын

​@@bintangramadan3217Send the vid pls

@boblol1465

22 күн бұрын

yes it is uploading the model into redstone dw

@KiwiRedstone

22 күн бұрын

At least...

Really great video. Also you demonstrate how easy making a neural network can be. You just explained everything very well. Will inspire people. Inspired me.

So a really cool detail is how you handle the floating point limitation, this is actually really close to some quantitation solutions, look at the paper : "The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits" if you have the time, you might find further optimizations there

I’m a time traveler and mattbatt has recently made a human brain in Minecraft

@Meyer-gp7nq

17 күн бұрын

He also made a Time Machine in Minecraft which is how you’re here I assume

@NimproductionsYT143

17 күн бұрын

@@Meyer-gp7nq Naturally

So... For all of you without experience with neural networks, this isn't a whole thing (not even close). He is placing weights which he already got from training in Python. Even though this is impressive, it's way less impressive than some of his other builds. Training a neural network would be impossible in Minecraft because of all the math it requires which isn't possible (or extremely hard and slow) in Minecraft... I hope I cleared things out :)

@Dimitri_gdr

22 күн бұрын

You're right, but had to do that and the result is still pretty cool

@andreabassi4521

22 күн бұрын

It's not impossible, maybe with a lighter neural network the training process will be possible.

@teabow.

22 күн бұрын

it's a neural network

@TheKastellan

22 күн бұрын

I mean it pretty obviously isn't the whole thing, and regardless it is still impressive. Logical redstone is pretty much "just" how you chain different circuits together so saying that it is any less impressive doesn't really make sense. Also even if it is just hard coding the weights, it is STILL a valid neural network model. Weird comment.

@flameofthephoenix8395

22 күн бұрын

I'm not extremely familiar with Minecraft, but I suspect that second half of what you said, "extremely hard or slow" is more accurate, though there would of course be memory limitations of the computer itself being unable to store all of the redstone. However, assuming the world file isn't too large Minecraft should be Turing complete.

Dude this is so amazing. To have the skill to make a machine like this, understand the math and computations behind it, minecraft knowledge, and the video production after it all? That's amazing

You’ve outdone yourself again, great Job! 🙌🏻

bro casually invented quantization by himself 💀

so basically you're creating AIs from binary 💀

This is such an amazing work I even applauded when the video ended. While watching the showcase I noticed that the 8 was always on the same confidence range, could this be a bug? Anyway this is incredible, Congratulations!!

Okay the bit shift caught me off guard. Absolutely amazing work

this is absolutely crazy, as someone who took machine learning in uni i never thought that this was possible in minecraft, mind blown!

You are crazy. Amazing work. And also getting a sponsor. Nice work man

The first time I understood such a viedo! thanks! and please keep going!

Finally found the perfect build for my base's front door combination lock

you never fail to amaze us, insane work!

this is amazing showcase of what a NN is and how it works. i worked with NN's for years and i still struggle sometimes lol

Yep definitely cool. You just said about integers being needed for minecraft and I'm thinking so you just multiply it up... sounds obvious but its only because you were already talking about it. So good.

It felt like I am watching Alan Turing solving making enigma. Keep creating this kind of content.

I'm IT student too and it's soo amazing to watch!

I finally understand how these neural networks work. Thank you!

Before we know it someone's gonna create actual LIFE from just redstone

The machine looks like the deciphering machine from the "the imitation game" You are good man.

insane love your work

Although I didn't actually understand what you were doing, it's always fascinating how those people like you has pushed the minecraft redstone community so far. Keep up with your work!

@RGpro9882

8 күн бұрын

Simple words, he made Ai

this is so cool, if there's even the slightest possibility to collaborate on a similar idea or project I'd be honored at such an opportunity

Awesome job and great explanation