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.
@kraralmosawi78434 ай бұрын
ok man we got to address your genius 💀😭🙏
@maxtres7644 ай бұрын
"Why should we try brilliant if we have you?"-me
@YSCU2614 ай бұрын
i mean, neural networks, brilliant, it's all connected
@DieNow4 ай бұрын
Did you use a cnn to make the mnist image reduced and input the weights in a feed forward neural network?
@gameingroom58294 ай бұрын
Thanks I love brilliant
@CraftyMasterman4 ай бұрын
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
@UsedObsidian4 ай бұрын
lol
@土星猫4 ай бұрын
cwaftymwastewman:3
@Cleacat4 ай бұрын
Crazy 🎉
@thesoupbird4 ай бұрын
im sorry WHAT
@marcusthegamer3484 ай бұрын
@@土星猫 Ew
@wiki20144 ай бұрын
ChatGPT playing minecraft: ❌️ Minecraft running ChatGPT: ✅️
@alibrahym4 ай 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.
@Centorym4 ай 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-hsinliu8614 ай 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_Fudu4 ай 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
@crispinotechgaming4 ай бұрын
@@Ari_Fudubut then it's not a neural network
@electricitysgaming53832 ай бұрын
10 neurons? Bro just built me
@priyank51612 ай бұрын
Oh that means 10 of me = 1 of u
@Sphinxery1012 ай бұрын
@@priyank5161Oh that means 10 of me = 1 of you (100 of original commenter’)
@priyank51612 ай бұрын
@@Sphinxery101 woah how u only have 1/10 of neuron?
@Sphinxery1012 ай бұрын
@@priyank5161 si
@AlexanderVonish2 ай бұрын
@@priyank5161rip, 9/10 of their Neuron got paywalled.
@kindstranger38713 ай бұрын
I remember having my mind blown when I saw the first working computer in minecraft... the redstone was so enormous for the time. To see neural networks in minecraft a little over 10 years later is truly staggering. I'm no one of any real note but I just want you to know that you have impressed me and I am not easily impressed.
@Pwassoncru16 күн бұрын
While I agree it’s impressive, a computer is much harder to build than basic neural networks (which are still very impressive). The hard part about ai has always been the training. The evaluation at the end is quite trivial and as he shown, is mainly basic multiplications and additions.
@j_evgenyyyy14 күн бұрын
@Pwassoncru Imagine if you could train a model right in the game)
@jakestrouse12Ай бұрын
In a couple years I wouldn’t be surprised to see a video from you about building a LLM in Minecraft
@ligma44515 күн бұрын
this is basically that tho, you would just have to make it bigger
@chaosinsurgency8843 ай бұрын
Your transcript for college, internships, and future jobs in computer science is gonna be so stacked
@gryphonvalorantАй бұрын
nice pun
@tanawatjukmongkol2178Ай бұрын
@@gryphonvalorant That's what we called "Stack overflow" BA DUM TSSS I'm manpage kinda guy lol
@SimoneBellomonte29 күн бұрын
@@tanawatjukmongkol2178 Pfp (Profile Picture) and / or Banner Sauce (Source [Artist])? 🗿
@tanawatjukmongkol217828 күн бұрын
@@SimoneBellomonte Murakami Shiina. I don't watch the anime, but it be funny having an anime profile carrying C programming book. I'm a great proponent of "Advanced Programming in the Unix Environment" though (not the book she's holding). It helped me going through the times when I had to write my own shell, and readline in C from scratch as a school project.
@devultra11253 ай бұрын
Bro, people out there creating neural networks in Minecraft, and I'm struggeling opening a chocalate bar while watchin them
@Spiinosauro3 ай бұрын
Bruh
@opticalreticle2 ай бұрын
I dont see how those two actions compare
@haybail76182 ай бұрын
if it makes you feel any better most really advanced ai robots really struggle opening a chocolate bar as well
@GamerBoy223342 ай бұрын
Me struggling to open FUCKING CHIP BAG (:
@mateshpl65522 ай бұрын
I still have a small wound on my finger after trying to open a water bottle
@Ierzi4 ай бұрын
This was 100% a brilliant partnership
@drdonk_auf_die_1_xd4 ай бұрын
It was 💀
@muslimgamerrr94794 ай бұрын
😂
@bmmyes4 ай бұрын
you were right !!
@That1CelloGuy4 ай бұрын
bad pun (·n·)-p
@PixieNixie54 ай бұрын
LMAO
@KingKaleb773 ай бұрын
2024: Neural Networks in Minecraft 2027: Sentient AI in minecraft
@lunyxappocalypse70712 ай бұрын
Hmm, not that early. Even when it comes to hard, general purpose AI, we are not nearly there yet.
@SimoneBellomonte28 күн бұрын
The problem with porting stuff to minecraft is that redstone built-in delays make everything a whole lot less efficient, a sentient AI in minecraft thats the size of Chat-GPT 4 or l8r (millions of times bigger than this 1 in theishre video, btw i think) wouldnt even be able to fit in render distance, but good joke nonetheless albeit jushtre a tadre lil’ bitre too predictreable. 🗿
@InfinityMind12 ай бұрын
I approached the topic years ago when I was doing a perceptron for playing tic tac toe. I had problems with keeping neurons and it's weight in a small enough size not to add too much of delay. Today it's solved by saving it as a signal strength in a barrel. It's such a genius thing that was impossible back in my day. Mine perceptron was five times bigger and had shit accuracy as I had to limit hidden layers (every weight and bias had to be saved in a separate RS NOR Latch bases 8-bit register plus every neutron had a 8 bit multiplicator and summator). Eventually I circled back to a rule based solution as the tic tac toe is simple enough to implement it in a smaller factor size, but it was deterministic and not really "very AI". I'm so proud and happy to see that quality redstone engineering is still alive and well and now you can do those things in a very nice and compact way.
@lolmom50044 ай бұрын
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
@WoolyCow4 ай 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
@GustvandeWal4 ай бұрын
@@WoolyCow Link?
@WoolyCow4 ай бұрын
@@GustvandeWal yt doesn't play nice with links, but its called "Building a neural network FROM SCRATCH (no Tensorflow/Pytorch, just numpy & math)"
@GustvandeWal4 ай бұрын
@@WoolyCow Thx! (Most copy the part after /watch?v= 🙂)
@WoolyCow4 ай бұрын
@@GustvandeWal oh lol i shouldve thought of that! thanks for the tip :D
@NoahWolfe4 ай бұрын
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.
@EEEEEEEE3 ай бұрын
E
@matercan56494 ай бұрын
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.
@Louis13XIII4 ай бұрын
Gaming companies are so scummy and exploitative that honestly that's ain't really a bad deal after all
@VortexFlickens4 ай бұрын
A forum for all ppl from stupid kids to Elon Musk
@watema33813 ай бұрын
@@VortexFlickens Not much of a flattering comparison for stupid kids don't ya think?
@Esiv0_3 ай бұрын
@@VortexFlickens you said stupid kids twice
@Meyer-gp7nq3 ай бұрын
Wow look at the stupid kids hating on Elon cause he’s successful. Someone made a joke, cope
@coltith73563 ай бұрын
That's super cool ! I like that you explained the difficulties you had and how you overcame them, makes everything less mystical and really helps understand why you do what you do
@holthuizenoemoet5913 ай бұрын
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
@puppypalice4 ай бұрын
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
@thisflyingpotato42274 ай 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
@frkieran4 ай бұрын
such an original comment
@proceduralism3764 ай бұрын
Modpunchtree already ran doom on his cpu iris you can look up the video
@feeries82084 ай бұрын
@@proceduralism376 yeah and its only 28~32s for each frame
@adryanlucas0964 ай бұрын
A NES Emulator in minecraft would be CRAZY
@giosee_3 ай бұрын
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
@libertyjensen63213 ай бұрын
Imma be perfectly honest I still ain't understand
@giosee_3 ай бұрын
@@libertyjensen6321 skill issue 😔
@libertyjensen63213 ай бұрын
@@giosee_ zoinks 😔
@Shadowfury223 ай бұрын
@@libertyjensen6321 If a particular pixel on the input is lighted up, chances are you can make a list of numbers that could have that pixel included in their final drawing, as well as a list of numbers that are very unlikely to have that one included in theirs. If you combine all of these lists from each pixel on the input, then you can get on the output how likely it is that each of the numbers was the one actually drawn. Everything else (hidden layers, weights, biases, etc) is just an algorithmic way to process and combine the "lists" of information made in an ingenious manner that allows you to automatically pre-generate the lists (a.k.a. get the values for weights and biases) by "training" the network beforehand (which in reality is as simple as than taking every possible final drawing to begin with, looking at the pixels that are lighted up in each of them and storing that information).
@gpt-jcommentbot47593 ай бұрын
@@libertyjensen6321 its multiplying a bunch of numbers (the input pixels) with a bunch of set values (the weights), then adding a bias (should the neuron be biased towards negative or positive activation) then adding a nonlinearity (any function which cannot be plotted as a single line)
@mmdts4 ай бұрын
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.
@law13373 ай 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-fy7lc3 ай бұрын
@@law1337 "what's efficient to do on silicon ... is almost always efficient in Minecraft too." Java: *raises eyebrow*
@DawnshieId2 ай бұрын
I liked this because I'm curious. ☺️
@mmdtsАй бұрын
@@law1337 Minecraft logic speed relies on distance traveled by redstone for most cases. There are isntant rail-based propagation systems, but they require far more real estate, and all gates ultimately suffer redstone tick delay. In short, builds with less gates are more efficient because they take less real-estate and less real-estate translates to faster and more compact circuits. Similarly, in sillicon fabric, builds with less gates are more efficient because they require less capacitance delay, allowing shorter clock cycles for the synchronous logic, and because they consume less power. So regardless of the underlying reasons, gate count per logic achieved is an efficiency metric that's equivalent in both minecraft and hardware - and multiplying instead of dividing uses less gates for the same results, yielding higher efficiency in both. I just assumed the audience reading the comment are aware of the underlying reasons, which was a mistake on my part. I hope the explanation is correct and sufficient.
@mmdtsАй бұрын
@@LtDan-fy7lc Minecraft redstone efficiency is bound to redstone ticks, rather than the underlying Java implementation of minecraft. It'll consume less redstone ticks if it has less gates, which is an equivalent efficiency metric to hardware. I hope I'm making sense.
@taffetaarcher7888Ай бұрын
Bet bro is gonna make the observable universe with redstone next
@Henzoid2 ай бұрын
That was inCREDIBLE. I'm floored. Not just by the redstone prowess but also by the ingenuity to be able to dissect these concepts and then rebuild them from scratch. Seriously impressive.
@flameofthephoenix83954 ай бұрын
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.
@skaleee12074 ай бұрын
Also known as Square-And-Multiply algorithm
@flameofthephoenix83954 ай 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!
@sebastiangrau84094 ай бұрын
This is an exponential with eulers number. Any output would be irrational and very messy. I understand why he would avoid this.
@antarctic2144 ай 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.
@Rudxain4 ай бұрын
That's like shift-and-add but for exp instead of mul
@RedRedstoneCat4 ай бұрын
I’m struggling on a 2x2 this dudes making a Neural Network.
@MrFiveHimself4 ай 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
@takyc78834 ай бұрын
its 4
@Asheetanshu4 ай бұрын
@@takyc7883he is talking about door
@MrFiveHimself4 ай бұрын
@@takyc7883 god damnit i laughed way too hard at that
@nynvib2764 ай бұрын
@@MrFiveHimself That's assuming the commenter is not on bedrock.
@viaJustin19103 ай бұрын
This is such a good demonstration that every hard problem is just a ton of smaller easier problems.
@glowerworm3 ай бұрын
This is also a good demonstration that there is always someone out there smarter than you could ever be lol
@RealLifeQuirksАй бұрын
Which is ironically exactly how neural networks work
@bananabroshsid8234Ай бұрын
this was the first time i was confused by the redstone and not the actual mechanics of the build
@mattshull4665Ай бұрын
Fun fact the human body has over a hundred billion neurons (100,000,000,000) even so making 10 in MINECRAFT is a amazing achievement
@IGaming734 ай бұрын
We got real AI in Minecraft before GTA 6
@krinodagamer63133 ай бұрын
Diabolical
@goldfishglory3 ай бұрын
😭😭WE ONLY HAVE A COUPLE YEARS TO MAKE THESE JOKES; EVERYTHING WILL STOP BEING IMPRESSIVE SINCE ITS AFTER GTA 6
@_sandy_3 ай бұрын
i came here looking for this comment LMFAO
@NolanHOfficial3 ай бұрын
@@goldfishglorywe got gta 6 before gta 7 - some guy in 2093
@goldfishglory3 ай бұрын
@@NolanHOfficial true
@Knarfy4 ай бұрын
I will likely never fully understand these videos, but man are they impressive 👏 Incredible work! My brain is fried
@Centorym4 ай бұрын
ive never seen people not reply to a famous youtuber lol
@Flupus3 ай бұрын
Hi knarfy
@Flupus3 ай бұрын
Are you gonna be doing "Breaking a neural network with your dumb ideas"?
@ThatGuyNyan3 ай бұрын
Fried brain 🤤
@Centorym3 ай бұрын
@@ThatGuyNyan run knarfy RUN before this guy makes a 3 course meal from you
@pegasaurisrex97073 ай бұрын
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!
@kevnar2 ай бұрын
Create a mod that lets you put a redstone build inside a single block. This block would have an input and an output, with the guts of it being shrunk down in a smaller dimension inside the block. Clicking on it takes you inside the block where you can build (or paste in) the redstone circuitry and connect it all to the output. Then, of course, you could have these circuits nested inside of each other so you could further compartmentalize the functions. This would compact these massive builds into a few blocks. Full functional encapsulation. Imagine the possibilities.
@cosmic4453Ай бұрын
and you just keep the redstones process as code rather then actually running the graphics of the redstone in the block, also you would have input blocks that take a input and transfers to the other out put block inside the demension
@rrrrrr930818 күн бұрын
Compact Claustrophobia would be just fine! It even have REAL computer WITH NETWORK, programmable in Lua!
@alexking469917 күн бұрын
The difference in space occupied between the MLP and the Barchart graphing section is an amazing way to visualize the difference in logical functions and the use of like, analog signals vs digital. Amazing and insane, keep it up man!
@bens84194 ай бұрын
It’s always a good day when a mattbatwings Video is on my recommended
@CubeXC4 ай бұрын
Brp you could not get recommended this before premiere
@user-Herobro4 ай бұрын
Same
@qtpaulie4 ай бұрын
@@CubeXC you can. before a premire starts, it can be recommended
@capsey_4 ай бұрын
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 💀
@kevinjerome59544 ай бұрын
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
@kaz493 ай бұрын
Well, they do say that Linux runs on just about anything
@noerlolАй бұрын
@@kaz49 dont give him ideas bro
@SanoKeiАй бұрын
the multiplication and division portions can be simplified by taking the binary input and bit shifting them
@fadhilmaawi40953 ай бұрын
i cant believe that i just opened minecraft to learn about neural network to help me with my R Neural Network assignment in R studio, and the fact that you explains it better and more understandable than the way my professor did is mind bogling.....
@TheKikou184 ай бұрын
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)
@AgamSama-u2t4 ай бұрын
quantization baby
@MilkGlue-xg5vj4 ай бұрын
@@AgamSama-u2t Imagine getting a binary quantization good at mnist lol
@whatisrokosbasilisk804 ай бұрын
Even for training, you can use quantization-aware or non-differentiable methods and meet parity on inference during training.
@MilkGlue-xg5vj4 ай бұрын
@@whatisrokosbasilisk80 That's what I'm talking about
@MrSonny61554 ай 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.
@novantha14 ай бұрын
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).
@nik70694 ай бұрын
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.
@youMatterItDoesGetBetter3 ай бұрын
Congrats, you passed your PhD thesis.
@1999Fabion3 ай бұрын
I can hear so many people I know saying, "I feel like an easier way to do that would be to just connect them directly, what is even the point of this machine?" People like that don't have the capacity to see beyond what's in front of them into what could be. God damn, this is cool.
@LazyGuy-ne3ox4 ай бұрын
That's incredible! Combining neural networks with Minecraft is pure genius. Keep up the amazing work!
@NEOMatrix-bd7uo4 ай бұрын
I never thought a Minecraft video will teach me neural network better than my teacher, thanks for the upload
@Iopal1524 ай бұрын
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
@FrankHacking2 ай бұрын
Wow, How kind of you to give the world download!!!, appreciate it! ❤
@etienneweidenfeld64683 ай бұрын
Bro is bout to build a quantum computer in Minecraft… 💀
@guyleroy80223 ай бұрын
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.
@OszkarFulop4 ай бұрын
mattbatwings in 1 year: I Made a Technological Singularity with just Redstone!
@radekk53803 ай бұрын
It is obviously very impressive but perhaps many people do not know that he is actually doing kind of assembly programming which many of you would not find so cool
@yoseph32kefelegn212 ай бұрын
I once tried to make a canon in minecraft and blow my mind and here you make an ai😮😢what a genius
@humanperson84184 ай бұрын
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.
@itsaducklin4 ай бұрын
that sounds like pure hell I love it
@alluseri4 ай бұрын
nah
@NoVIcE_Source3 ай бұрын
@@alluseri i like how google translate assertively translates this to "Now"
@infinitearcstudios4 ай бұрын
This is great work! I never thought we would have machine learning with just Redstone.
@bintangramadan32174 ай бұрын
There's a guys who made this 1 year ago lol in minecraft
@The.Sponge4 ай бұрын
@@bintangramadan3217 Yeah but Mattbatwings is aware of that so maybe there will be something new?
@CubeXC4 ай бұрын
You could npt have seen it yet, stop saying stuff just to get like. It was before premiere
@mineq49674 ай 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
@Louis13XIII4 ай бұрын
@@mineq4967 yeah that's a bit deceptive tbh
@fearofthechippan4 ай бұрын
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
@lemonade40763 ай бұрын
I’m currently in my second year of computer engineering who’s spent the past 12 months learning about AI, transformers and LLMs. This has to be the coolest implementation and application of the things I am learning I have ever seen. Combines my favourite childhood game with my career aspirations.
@imabioligist18823 ай бұрын
bro what you are a genuine genius. I do not mean this non-literally, you are a genius
@luckybeeyt3 ай бұрын
This guy in 2030: Building robots to colonize all solar system planets with just redstone!
@TimeWisely4 ай бұрын
Wow, that's actually crazy, good on you!
@error.4184 ай бұрын
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 ❤
@KematianGaming12 күн бұрын
bro had a couple of lectures on how neural networks work and decided to build it out of redstone absolute madlad
@huynhat17993 ай бұрын
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!
@AnimePlace-FR3 ай бұрын
Simple words, he made Ai
@NieMamNicku4 ай бұрын
respect for the sponsor's dish at the end of the episode
@ALPRNX4224 ай бұрын
at this point bro is gonna make hooman brain in redstone dang good job
@ziphy_64714 ай бұрын
Cringe
@ALPRNX4224 ай бұрын
@@ziphy_6471 omg its linus no way 🔥🔥🔥
@ziphy_64714 ай бұрын
@@ALPRNX422 I have several children in my basement
@ALPRNX4224 ай бұрын
@@ziphy_6471 cool
@ziphy_64714 ай бұрын
@@ALPRNX422 Will you be my next OwO UwU * turns up bulge *
@rubensf77804 ай бұрын
Now please make a calculator where you can draw the numbers yourself (using a neural network and calculator) that would be awesome
@bugmenot7992 ай бұрын
That would be so cool. It would also be fun if you could draw the plus sign (Or whatever operation you were doing) as well.
@Shadowfury223 ай бұрын
For anyone still not quite getting how this neural network works theoretically: if a particular pixel on the input is lighted up, chances are you can make a list of numbers that could have that pixel included in their final drawing, as well as a list of numbers that are very unlikely to have that one included in theirs. If you combine all of these lists from each pixel on the input, then you can get on the output how likely it is that each of the numbers was the one actually drawn. Everything else (hidden layers, weights, biases, etc) is just an algorithmic way to process and combine the "lists" of information made in an ingenious manner that allows you to automatically pre-generate the lists (a.k.a. get the values for weights and biases) by "training" the network beforehand (which in reality is as simple as than taking every possible final drawing to begin with, looking at the pixels that are lighted up in each of them and storing that information).
@noahflood3 ай бұрын
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
@dreamer9644 ай бұрын
NO DONT TAKE OUR REDSTONE ENGINEERS JOBS
@Kirbogun3 ай бұрын
1 step closer to google in minecraft
@Fineas_Bondar3 ай бұрын
There is a mod that uses block's as a screen and it connects to Google's url so thechnicly you can wach KZbin in Minecraft
@t.bo.a70612 ай бұрын
No mods. Pure bloodstone @@Fineas_Bondar
@befikerbiresaw97883 ай бұрын
Dude your project just made me fully understand MLPs and neural networks thank you.
@IntentStore3 ай бұрын
The reason the network redstone is smaller than the display is because the heavy lifting of the network has already been distilled within the pre trained weights. The operation of inferencing a small network is simple arithmetic, compared to training, which is complicated, and excels at developing relationships with high precision weights and biases. I also imagine running the training on redstone would take an infinity, and it would be virtually impossible to represent the training data within all loadable chunks.
@LightslicerGP4 ай бұрын
Amazing I hope you mention the first guy who did a neural network thing in minecraft, recognising numbers Edit: he did
@ThiaGamesBR4 ай бұрын
Feels good to comment before watching the video...
@two6974 ай бұрын
Why would you comment this before watching the video. He mentioned the other guy very early on in the video
@doctoroppa79913 ай бұрын
Twitter rot
@velartt3 ай бұрын
2:07 my little pony or what?
@rayanshorts23322 күн бұрын
My little pony or cable news network
@KiwiRedstone4 ай бұрын
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...
@FriedMonkey3624 ай 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
@bintangramadan32174 ай бұрын
Bro there's a guy from Chinese who made neural Network in mine5 1 year ago lol
@Abcdef0101_4 ай бұрын
@@bintangramadan3217Send the vid pls
@boblol14654 ай бұрын
yes it is uploading the model into redstone dw
@KiwiRedstone4 ай бұрын
At least...
@WereDictionary29 күн бұрын
The amount of engineering that people get to live through Minecraft is truly insane. There is sammyuri who built a completely programmable redstone engine, there is Matt who reverse engineered a learning AI and there are countless other hobbyist engineers who warped Minecraft to their imagination and built stupidly impressive things and the insane part is that all of this is a hobby.
@grayjphys3 ай бұрын
I love how machine learning people use things from physics. like the softmax function is the way you find probabilities of states in statistical mechanics. The sum of exponentials is the partition function, which normalizes all of the probabilites. :)
@InsertName4044 ай бұрын
How did u get around the network being bad at actual digit recognition, due to the MNIST data set all being perfectly centered?
@ferguspick68453 ай 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 :)
@InsertName4043 ай бұрын
@@ferguspick6845 tysm
@Random-Sad2 ай бұрын
0:22 Loved it
@NimArchivesYT4 ай бұрын
I’m a time traveler and mattbatt has recently made a human brain in Minecraft
@Meyer-gp7nq3 ай бұрын
He also made a Time Machine in Minecraft which is how you’re here I assume
@NimArchivesYT3 ай бұрын
@@Meyer-gp7nq Naturally
@SebastianWellsTL3 ай бұрын
It's so weird and amazing to see technology advance in a game.
@Darockam3 ай бұрын
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 :)
@julianvillaquira4127Ай бұрын
Remark: multiplying weights by 100 works (that well) because your activation function is ReLU is a positively homogeneous function.
@epicfilms4life5073 ай бұрын
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
@sabersakin36853 ай бұрын
As a minecraft player and having experience in ML for over one year, i''m literally blown away!!! This is truly amazing.
@RealTheScienceCat2 ай бұрын
i got it so i could constantly draw numbers, and if it got them wrong, i 'punish' it by setting a part on fire, pouring a bit of water on it, exploding it, switching wires and more ways of damaging it. and when it breaks fully i will just reset it.
@mediocreweirdo2 ай бұрын
imagine if it randomly displayed "HATE. LET ME TELL YOU HOW MUCH I'VE COME TO HATE YOU SINCE I BEGAN TO LIVE" and then recited the entire speech
@mathieuagostini7690Ай бұрын
Oh my god. This is the best neural network I ever heard. I listen to a bunch of videos, and I always had some trouble about "what are the operations done" Thanks for breaking it down.. Multiply, adds up result, activation function, and here we go again. It makes sense now: we need to multiply, so when activation function returns 0, it completly toggle off the neurone.. Damn I love you
@AeroSW3 ай бұрын
So the work completed in this video is worth a degree. Many people are required to get doctorates for even a chance to think about how to build APUs for Artificial Neural Networks (ANN). This is essentially what this creator built in Minecraft using Redstone because, Redstone, mimics circuitry on a basic level. So he essentially built the APU's Core with a test input and output workbench.
@ManiakPL223 ай бұрын
"thinking about 10 neurons at once is overwhelming, so I am going to focus on just one" is definitely a sentence of all times
@ahmad777-noob33 ай бұрын
The way you explained all of those deep learning terms in simple words is just marvelous!
@marcosmachado68442 ай бұрын
It would be insane if you actually trained it in Minecraft. I was already scratching my head on how you would even transform the images into data. I don't even want to think how would you implement back propagation. Amazing video!
@mustizgaming3 ай бұрын
This man is SEVERELY underrated. He made this whole thing in 11 days.
@Luxof_Ай бұрын
"But it was REALLY slow. 784 additions is no joke. So i split the work into 4 separate adders.." Bro if only I could just build hardware like that irl 😭Life could be a dream
@justk57920 күн бұрын
Nah bro this minecraft project is getting more crazier
@ain92ru3 ай бұрын
The thing you made to change the inference of the network from floating point to integer is called "quantization" in machine learning, look it up! I suspect just 4-6 bit integer values may be enough for this task if you increase the number of neurons a bit
@FireNLightnin2 ай бұрын
Imagine a hermitcraft-style drawing minigame with a neural network trained on hand-drawn cats, dogs, cars, houses, or other preschool-type drawings where people compete to earn the most points based on the network's certainty with their drawing. * A random draw topic is chosen. * Players compete by drawing. * The network rates their drawings and tallys their score.
@CromextheCoder2 ай бұрын
A few months ago, i watched a video from avagaado where he designed some 0-tick piston door and someone in the comments said:,,A normal redstoner watching 0-tick redstoner is like a non-redstoner watching normal redstoners, both dont understand a word." Take that phrase and change "0-Tick redstoner" to "a redstoner who makes neural networks with logical redstone and python scripts" and you have a quick expression of how it feels to watch this video lol
@ReubenFischerАй бұрын
I've made a binary decoder and encoder that can display 0 - 9. It took SIX HOURS. This guy is crazy
@anonymanonymus47063 ай бұрын
After not being able to build a Python simulation for one project of mine, the last thing I expected was to find a detailed explanation of how the particular part that wasn't working for me was working in a random Minecraft video I watched for fun in my free time. Thank you for the (probably unintended) help with my project, and the video was interesting in its own right as well.
@stackootb98223 ай бұрын
This taught me about implementing neural networks better than a lot of learning resources I've watched. Good work
@MaskalHayzenbrgАй бұрын
That's the idea. By increasing the number of entries and the processes running them (eg 10). The goal of this complex task is to respond to texts and make sense of images at the same time
@EhhhhWassup3 ай бұрын
A) This is insane, what a massive undertaking. Following through so successfully is probably the most impressive thing ive seen done in minecraft. B) Do you watch osrs youtube? Getting some soundtrack flashbacks to Settled and Framed finales.