This video is about a simple algorithm to experiment with basic AIs. Thanks to Alexislouis for the music! @alexislouis2320 You can find the music here: / 18zvih9nrh8gtkjy9 Github github.com/johnBuffer/Pendulu...
Пікірлер: 265
@alexislouis2320Ай бұрын
Nice video my friend. I would stay around for the seconds parts guys, exciting things ahead ;)
Ай бұрын
fr
@mox189Ай бұрын
BASED
@GuildOfCalamityАй бұрын
I could be insane, but I would swear that a rooster just taught me AI.
@bradley1995Ай бұрын
He did, and a cock a doodle too!
@sebastianpohl12687 күн бұрын
Twist at the end: The rooster was itself an AI ...🤔
@CraftingCat_IXАй бұрын
The talking chicken is *slightly* cursed. It’s probably because only the beak is moving and it’s opening a bit too wide for my taste.
@plaintext7288Ай бұрын
+ the balls like red things
@the-bgrspot6997Ай бұрын
hyper cursed tbh
@poultrypantsАй бұрын
and the balls 🤣🤣
@sumitbiswas164Ай бұрын
Extremely distracting! I would prefer relevant scenes in a serious video.
@volblaАй бұрын
I like the chicken. I find it charming :>
@alliepiper4772Ай бұрын
I'm finally starting to recover from like 3 years of intense burnout as a software engineer, and watching your videos helps me remember why I got into this field in the first place. Looking forward to the next one!
@grahamsnyder762Ай бұрын
Since the controller can output an arbitrary cart speed every timestep, it is permitted more or less infinite acceleration. It would be interesting to see how they perform if the available acceleration, (or power, or whatever) is constrained to realistic bounds
Ай бұрын
That's actually pretty standard to alter into a categorical/discrete step.
@knitnatsnokprogrammingАй бұрын
He’s alive!
@thebetterbutter709Ай бұрын
From a frenchmen to another, your accent has improved so much! Your videos are captivating as always.
@proyoloks1386Ай бұрын
yeah it's insane, I almost forgot that this is the same guy as 8 months ago...
@mr.ditkovich9983Ай бұрын
Can't wait to see your next video 🙌🏾🙌🏾
@TheTechnopiderАй бұрын
Extremely excited for the next video! For some reason, AI training videos just scratch a certain itch so nicely
@Oring17Ай бұрын
Love your work Pezzza. You are a great inspiration.
@knitnatsnokprogrammingАй бұрын
I’ll binge-watch this rn
@ruolbuАй бұрын
how do you binge a single 13 minute video?
@knitnatsnokprogrammingАй бұрын
@@ruolbu By rewatching it over and over again at 0.25x speed
@PezzzasWorkАй бұрын
Amazing
@ruolbuАй бұрын
dedication
@PloverTechOfficialАй бұрын
This is amazing! I can actually understand how to create my own system if I wanted. Unlike some videos which don’t succeed at telling us in an understandable way.
@Hailfire08Ай бұрын
Love your videos and can't wait for the next one!
@xernas7880Ай бұрын
Finally ! I just love your content, i'm happy to see you again, also on my favorite topic
@mnajjar855 күн бұрын
the visualizations are epic
@notthetruedmАй бұрын
I love how you animated this! It looks so cool and made it easy to follow along
@IbloopАй бұрын
I was literally about to work on a project of mine that requires AI, immaculate timing pezzza
@dedelblute3946Ай бұрын
I love this channel. It's enjoyable to just watch cool coding stuff.
@issamoudriss6564Ай бұрын
This video is super nice man, waitin for the second part!
@karlosfyАй бұрын
Really inspiring. Will be waiting to see the code! Great content :)
@simon_aviationАй бұрын
Thank you SOOOO MUCH!!!! I always wanted to do something like this, this will really help!!!
@rigbybАй бұрын
Great video! Glad to see you again
@elex6934Ай бұрын
I love your videos ❤ ai is such an interesting topic and I'll watch part2 as soon as possible
@user-lm4nk1zk9yАй бұрын
Now build entire ecosystem with Darwin's evolution principles.
@Maus_IndahausАй бұрын
I'd like to see that!
@SystemBDАй бұрын
That is actually a branch of classical AI called Evolutionary/Genetic Algorithms. They are not hard to code, but they have limited applications.
@Me-0063Ай бұрын
@@SystemBDNot hard to code is an understatement. In my opinion, its probably the easiest to code from scratch…
@allanburns1190Ай бұрын
I am actually working on something similar
@TVDaJaАй бұрын
@@Me-0063 They sound to me like a normal neural network that uses random noise and a kind of selection instead of a more guided training algorithm
@JayBenOhАй бұрын
Great video! It's a very nice visual representation ... that must have been a ton of work!
@namdao2672Ай бұрын
im trying to learn ML and DL by myself and find this super helpful, waiting for your next masterpiece
@srb9767Ай бұрын
Your projects are amazing, and often very beautiful. I aspire to make software as good as this one day!
@WolforceАй бұрын
Great video! as always!
@NickCombsАй бұрын
The first steps are always the hardest, so it might be good to show some actual code examples for them.
@CraftingCat_IXАй бұрын
The guy is back :D
@sourabhk2373Ай бұрын
Videos like these remind me why I got into this field. Man my job is sucking the soul out of me. Gotta do something about this.
@brickstopforallАй бұрын
I was wanting a video on machine learning!! It's from you aswell!
@SakejoАй бұрын
In the next videos I suggest including some articles, in the description, to delve deeper into the topics discussed. As I was searching for the sources for this project, I couldn't find them.
@ZeroPlus707Ай бұрын
Great video! Hyped for the double pendulum :)
@loicsen8003Ай бұрын
Very nice video, thanks for that
@gedaliakoehler6992Ай бұрын
Very neat (haha)! Also great classical controls problem!
@midasscheffers7610Ай бұрын
Awsom video, cant wait for the second part
@allanburns1190Ай бұрын
This will actually help me so much in my new project
@motbus3Ай бұрын
Loved the UIs
@khatharrmalkavian3306Ай бұрын
Double pendulum should be fun. I wonder how good a solution it will be able to find. As an aside, can't you just use the raw pendulum height (summed per frame) as a fitness function?
@wjrasmussen666Ай бұрын
That is fun! Good work
@codedeusАй бұрын
Great video as usual :D
@abdulrahmanelawady4501Ай бұрын
Thank you for a great video
@marcelob.5300Ай бұрын
Wonderful!
@Blooper1980Ай бұрын
Very neat video
@MysteryPancakeАй бұрын
nice! it reminds me of the MarI/O video, it uses this algorithm too
@sofia.eris.bauhausАй бұрын
inverted double pendulum sounds intense! looking forward to it. :)
@i_do_stuffАй бұрын
Waiting for the next one!
@enderdodo974923 күн бұрын
Very interesting video! The editing and animations are so nice and makes it easy to understand, and I was wondering, what software did you use to make them?
@yraharchenko6364Ай бұрын
soooo, now I want to watch the next video, it is so excited
@Leonan-cx6dlАй бұрын
Waiting for the next video!
@ScienceGuidesАй бұрын
Great work! :-)
@CyrilM68Ай бұрын
I can't wait to see what happens next with the double pendulum !
@kinsondigital20 күн бұрын
What would be neat is to take an AI model that has been trained in realist physics and see if it can be applied to balance a real-world physical pendulum. There are forces and things in real-world physics that you cannot account for in a software simulation. For example, there are electrical forces, such as wire resistance, with the electric motor that drives the cart. The friction forces of the rail and the cartwheels, forces of wind if the balance operation occurred in an outside windy environment, and more. It would be fun to build something like this and train a model to control a real-world pendulum!!
@g3itnalАй бұрын
im excited for the next video
@teenspirit1Ай бұрын
I do topological sorting, but then I cache all the pathways from input nodes to output nodes into lists. This way, instead of re-iterating the graph, I just do a for loop to iterate over lists of nodes instead of repeatedly recalculating paths. I haven't seen this technique used online but it makes training step much faster.
@Prism01921 күн бұрын
Yeah, that popped out to me as an immediate speedup opportunity. Just gotta make sure it's only valid while the topology of it doesn't change. (Maybe invalidate it in the "add node/connection" mutations)
@chrisdickens4862Ай бұрын
Very cool!
@manamimnmАй бұрын
That trippy music!
@Koroistro22 күн бұрын
I always found these systems fascinating, adding noise made me wonder about one thing: what if there was noise on the neurons themselves? In the real world neurons live in a chaotic systems too, so it stands to reason that there'd be sources of noise there too.
@happycolours8551Ай бұрын
Yay he's back
@QwertyIsCoolАй бұрын
Hes back lets go!
@noahwinslow3252Ай бұрын
I'll admit I wasn't as interested in this one as your other work, but your animation quality is *chef's kiss* such a good presentation
@shadowcrafter01Ай бұрын
That's an awesome video. Crazy good graphics! Mind giving us a hint on how you made them?
@PezzzasWorkАй бұрын
Thank you! I am using C++ and SFML, I will probably make a series of small tutorial to explain how I do this
@P4INKillersАй бұрын
This is an absolutely wonderful video. If I may provide some feedback; It would be great if you could visually show how these mutations (5:47) are applied using the network chart. When splitting an existing connection in two, do they share the same connections with their parents and children? Do new connections have random weights? Also, why does my hyperbolic tangent function provide values different from yours?
@synterrАй бұрын
So cool example! Can't wait to see how AI will handle chaotic pendulum ;)
@ihv2010_ccАй бұрын
YES :D
@quantumgaming9180Ай бұрын
I did not expect you to say "double pendulum" and now you are leaving us on a cliff hanger like this :( Hope next episode appears soon
@bradley1995Ай бұрын
This video seems much simpler than your others. Although I hope a bit more math and code examples can be used in the next. Gate logic videos seem great to teach the subject aswell. Although I feel such simplicity makes it hard to understand the topic clearly enough to extend it to more complicated matters.
@antoinespadone7834Ай бұрын
amazing work and i hope mine will work
@mikelColdАй бұрын
What a hook!
@GunnahanАй бұрын
cant wait for part 2 🙂
@BanaannaaАй бұрын
same
@motbus3Ай бұрын
I'm still curious about the UIs :) anxiously waiting for the source code ❤
@jmcglockYTАй бұрын
yes he uploaded
@RaduАй бұрын
Nice one!
@PezzzasWorkАй бұрын
Thank you! I am really impressed by your understand ai videos
@RaduАй бұрын
@@PezzzasWork you've seen those? Cool, thanks for watching :-)
@alessi4249Ай бұрын
Yeah.. the talking cockerel with sunglasses talking about NN is weirding me out.. Great video!
@gustavoadolfomelindresАй бұрын
Yay!!!
@QQ-jn5jbАй бұрын
The talking chicken is amazing
@ryshaskАй бұрын
Talking chicken? I'm in!
@and_I_am_Life_the_fixer_of_allАй бұрын
such a crime that one of the best youtubers in the tech space only has 138k views and only 34k views on this video after 7 days
@jayearl3591Ай бұрын
So after all these months in hiding, you've been secretly building Boston Dynamics Spot knock-offs 😂
@geobruce1995Ай бұрын
This was again an awesome and beautifully visualised video, just like I'm used from this channel. I'd love to be able to program something like this. If you were to make a more detailed tutorial that we can follow along with the videos and description I believe many people might benefit from this. Is your code open source? Thanks a lot for your awesome content!
@ardumaniakАй бұрын
Hurry up with the second part, I can't wait!
@chris.hinsleyАй бұрын
Was nice to see a none layered net ! But just a DAG net.
@thatprogramerАй бұрын
Very well explained! I wonder how the network would react to slight random fluctuations in the value of the nodes or just straight up removing nodes (How would it adapt?)
@Yeetmaster982Ай бұрын
im exited to see it with a double pendulum
@Alexander20091988Ай бұрын
Really cool video, thank you! This is an really interesting sub topic of ML, especially with such simple networks. Im wondering how it would play out, to create some intermediate game ai, which handles some decisions with this sort of mechanisms instead of a huge load of switch/if/else shenanigans. Obviously not driven fully by it for performance reasons, but in an assisting way. Btw, can you add the used resources (wiki/paper links) to the description? I would appreciate it. Thank you!
@tatomans198223 сағат бұрын
excelent video. I learn a lot. Do you have any video where you explain the code?
@jazzargamer306423 күн бұрын
That's amazing. I really like what you have done here. Can you share some of the code used in this video? It would be appreciated.
@Antcode-wk7tu29 күн бұрын
Hi Pezzza. I have got a question for a physics rigid body particle simulation you made ages ago, and I am dying to know since you didn’t upload the source code and can’t find what I need anywhere else. You have the feature where you are able to draw your own rigid bodies with the mouse. I believe the objects are composed of particles which are interconnected by constraints (correct me if I am wrong). I know how to implement everything apart from the constraint connections. How do I connect the particles in a way that works for any drawing and keeps the object's rigidity. A naive approach be to connect every particle to every other particle but that would suffer from performance issues. How did you implement it?
@FailRaceFanАй бұрын
I feel like I've learned more in this video than in 5 hours of reading. Will you also talk about other learning algorithms?
@PezzzasWorkАй бұрын
Yes I will explore other methods!
@lennarth.6214Ай бұрын
I really like the NEAT-algorithm and its variations. I've used them to find shapes for the unsolved mathematical problem called moving sofa. I got something similar to the currently known best solution in just a few dozen iterations. I wonder how this algorithm scales with more complex task on just a few inputs.
@FunkyTurtleАй бұрын
awesome video man, the graphics are super beautiful as always. you inspired me to make a network of my own, what sources did you use to learn the intricacies of the architecture? i understand the general flow but wouldn't know when at what rate should i add connections or nodes. thanks 😄
@PezzzasWorkАй бұрын
Thank you! I did use the original paper a lot and then tweaked things a bit to feet my needs. In the end these parameters have quite a lot of flexibility, there is a wide range of possible values that can lead to good results. In this case I used 5% chance to create a new node and 50% chance to create a new connection.
@kojoxАй бұрын
babe wake up, we got to watch this now
@azuky74Ай бұрын
I wanted to do the same (create my own evolution neural network) for a long time and you gave me the motivation to ! Thank a lot Your video is really great ! Love it ! I have one question, on my side I have one issue. Network are get over complexed really fast, creating many neurons in fact not necessary. How did you managed this ? Do you decrease the chance to create a new neuron depending on the current number ? Do you take the size of the network in account when scoring ? Or maybe you didn't have this issue ! If anyone have an idea about it, I take it ! (I resolved the issue by decrasing the score depending on the network size, but I'm not feeling this is a good way to solve it)
@AannoonnnnАй бұрын
G ❤️🔥
@zyro8473Ай бұрын
+1 for part 2
@bergolhoАй бұрын
Congratulations for the video! Could you please tell me which software you use to build the animations ?
@PezzzasWorkАй бұрын
Thank you! I am using a C++ tool I wrote myself
@user-ns7fz5gb5pАй бұрын
Nice work! Is it possible that you publish this project would very interesting to read the code.
@PezzzasWorkАй бұрын
It is planned, I am currently cleaning the code
@user-ns7fz5gb5pАй бұрын
@@PezzzasWorkThanks
@julianxeАй бұрын
Super insightful! What tool are you using for animations?
@PezzzasWorkАй бұрын
I did create my own tool using C++ and SFML
@moofin4170Ай бұрын
In theory I understand training AI, however what software do you use? Where do you write logic? How do you get an image output? How do you offload the work to a GPU for faster matrix processing? Interesting stuff, nonetheless. Great video!