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 I will release the code of demo shown in the video later.
Пікірлер: 223
@alexislouis232014 күн бұрын
Nice video my friend. I would stay around for the seconds parts guys, exciting things ahead ;)
2 күн бұрын
fr
@GuildOfCalamity14 күн бұрын
I could be insane, but I would swear that a rooster just taught me AI.
@bradley199511 күн бұрын
He did, and a cock a doodle too!
@CraftingCat_IX14 күн 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.
@plaintext728814 күн бұрын
+ the balls like red things
@the-bgrspot699714 күн бұрын
hyper cursed tbh
@poultrypants14 күн бұрын
and the balls 🤣🤣
@sumitbiswas1648 күн бұрын
Extremely distracting! I would prefer relevant scenes in a serious video.
@volbla7 күн бұрын
I like the chicken. I find it charming :>
@knitnatsnokprogramming14 күн бұрын
He’s alive!
@alliepiper477213 күн 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!
@grahamsnyder76214 күн 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
11 күн бұрын
That's actually pretty standard to alter into a categorical/discrete step.
@user-lm4nk1zk9y14 күн бұрын
Now build entire ecosystem with Darwin's evolution principles.
@Maus_Indahaus14 күн бұрын
I'd like to see that!
@SystemBD14 күн 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-006314 күн бұрын
@@SystemBDNot hard to code is an understatement. In my opinion, its probably the easiest to code from scratch…
@allanburns119014 күн бұрын
I am actually working on something similar
@TVDaJa14 күн 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
@thebetterbutter70913 күн бұрын
From a frenchmen to another, your accent has improved so much! Your videos are captivating as always.
@proyoloks138611 күн бұрын
yeah it's insane, I almost forgot that this is the same guy as 8 months ago...
@mr.ditkovich998314 күн бұрын
Can't wait to see your next video 🙌🏾🙌🏾
@Oring1714 күн бұрын
Love your work Pezzza. You are a great inspiration.
@xernas788014 күн бұрын
Finally ! I just love your content, i'm happy to see you again, also on my favorite topic
@Ibloop14 күн бұрын
I was literally about to work on a project of mine that requires AI, immaculate timing pezzza
@Sakejo10 күн 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.
@Hailfire0814 күн бұрын
Love your videos and can't wait for the next one!
@knitnatsnokprogramming14 күн бұрын
I’ll binge-watch this rn
@ruolbu13 күн бұрын
how do you binge a single 13 minute video?
@knitnatsnokprogramming13 күн бұрын
@@ruolbu By rewatching it over and over again at 0.25x speed
@PezzzasWork13 күн бұрын
Amazing
@TheTechnopider12 күн бұрын
Extremely excited for the next video! For some reason, AI training videos just scratch a certain itch so nicely
@notthetruedm12 күн бұрын
I love how you animated this! It looks so cool and made it easy to follow along
@issamoudriss656410 күн бұрын
This video is super nice man, waitin for the second part!
@NickCombs13 күн бұрын
The first steps are always the hardest, so it might be good to show some actual code examples for them.
@dedelblute394614 күн бұрын
I love this channel. It's enjoyable to just watch cool coding stuff.
@karlosfy9 күн бұрын
Really inspiring. Will be waiting to see the code! Great content :)
@rigbyb14 күн бұрын
Great video! Glad to see you again
@quantumgaming91808 күн 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
@elex693414 күн бұрын
I love your videos ❤ ai is such an interesting topic and I'll watch part2 as soon as possible
@CraftingCat_IX14 күн бұрын
The guy is back :D
@srb976714 күн бұрын
Your projects are amazing, and often very beautiful. I aspire to make software as good as this one day!
@ZeroPlus7079 күн бұрын
Great video! Hyped for the double pendulum :)
@PloverTechOfficial11 күн 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.
@simon_aviation14 күн бұрын
Thank you SOOOO MUCH!!!! I always wanted to do something like this, this will really help!!!
@JayBenOh13 күн бұрын
Great video! It's a very nice visual representation ... that must have been a ton of work!
@noahwinslow32529 күн 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
@Wolforce14 күн бұрын
Great video! as always!
@codedeus9 күн бұрын
Great video as usual :D
@abdulrahmanelawady45019 күн бұрын
Thank you for a great video
@midasscheffers761013 күн бұрын
Awsom video, cant wait for the second part
@namdao267214 күн бұрын
im trying to learn ML and DL by myself and find this super helpful, waiting for your next masterpiece
@khatharrmalkavian330614 күн 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?
@sofia.eris.bauhaus6 күн бұрын
inverted double pendulum sounds intense! looking forward to it. :)
@wjrasmussen6663 күн бұрын
That is fun! Good work
@motbus312 күн бұрын
Loved the UIs
@brickstopforall14 күн бұрын
I was wanting a video on machine learning!! It's from you aswell!
@i_do_stuff11 күн бұрын
Waiting for the next one!
@allanburns119014 күн бұрын
This will actually help me so much in my new project
@and_I_am_Life_the_fixer_of_all7 күн 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
@ihv2010_cc14 күн бұрын
YES :D
@CyrilM6814 күн бұрын
I can't wait to see what happens next with the double pendulum !
@yraharchenko636414 күн бұрын
soooo, now I want to watch the next video, it is so excited
@teenspirit113 күн 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.
@Blooper198013 күн бұрын
Very neat video
@ScienceGuides10 күн бұрын
Great work! :-)
@manamimnm12 күн бұрын
That trippy music!
@marcelob.530014 күн бұрын
Wonderful!
@gedaliakoehler699214 күн бұрын
Very neat (haha)! Also great classical controls problem!
@MysteryPancake14 күн бұрын
nice! it reminds me of the MarI/O video, it uses this algorithm too
@Leonan-cx6dl14 күн бұрын
Waiting for the next video!
@g3itnal14 күн бұрын
im excited for the next video
@chrisdickens486213 күн бұрын
Very cool!
@synterr14 күн бұрын
So cool example! Can't wait to see how AI will handle chaotic pendulum ;)
@QwertyIsCool14 күн бұрын
Hes back lets go!
@QQ-jn5jb14 күн бұрын
The talking chicken is amazing
@happycolours855114 күн бұрын
Yay he's back
@geobruce199513 күн 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!
@jayearl359113 күн бұрын
So after all these months in hiding, you've been secretly building Boston Dynamics Spot knock-offs 😂
@antoinespadone783412 күн бұрын
amazing work and i hope mine will work
@jmcglockYT14 күн бұрын
yes he uploaded
@motbus39 күн бұрын
I'm still curious about the UIs :) anxiously waiting for the source code ❤
@bradley199511 күн 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.
@P4INKillers13 күн 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?
@Gunnahan14 күн бұрын
cant wait for part 2 🙂
@Banaannaa14 күн бұрын
same
@Alexander2009198813 күн 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!
@thatprogramer11 күн 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?)
@alessi424913 күн бұрын
Yeah.. the talking cockerel with sunglasses talking about NN is weirding me out.. Great video!
@mikelCold9 күн бұрын
What a hook!
@gustavoadolfomelindres14 күн бұрын
Yay!!!
@lennarth.621414 күн 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.
@azuky748 күн 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)
@ardumaniak13 күн бұрын
Hurry up with the second part, I can't wait!
@FunkyTurtle7 күн 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 😄
@PezzzasWork18 сағат 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.
@chris.hinsley14 күн бұрын
Was nice to see a none layered net ! But just a DAG net.
@Aannoonnnn14 күн бұрын
G ❤️🔥
@ryshask14 күн бұрын
Talking chicken? I'm in!
@shadowcrafter0111 күн бұрын
That's an awesome video. Crazy good graphics! Mind giving us a hint on how you made them?
@PezzzasWork17 сағат бұрын
Thank you! I am using C++ and SFML, I will probably make a series of small tutorial to explain how I do this
@ziggyzoggin14 күн бұрын
48 seconds ago!
@Yeetmaster98214 күн бұрын
im exited to see it with a double pendulum
@gorlix11 күн бұрын
after this video you convinced me to play around with neutral networks. i quickly found my first goal - make MNIST number recognition network. its my second day trying and the network consistently gets 30% error rate which really pisses me off, this must be because i did not use any libraries and slapped it together on a Unity C# project with a help of chat gpt. im planning to run network on a separate thread so i could test more variety of settings for the neural network. anyways if you are reading this, what would you suggest for me? im using traditional neural network with inputs of 784 hidden layer 128 hidden layer 32 output layer 10 and learning rate of 0,0005 in each epoch it eats 60k images after running first half of first learning epoch it shows 25-30% error rate, after second epoch error rate tends to move closer to 50% which is weird, i tried making learning rate smaller but that requires lots of time too
@FailRaceFan12 күн 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?
@PezzzasWork16 сағат бұрын
Yes I will explore other methods!
@moofin417011 күн 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!
@bradb963514 күн бұрын
Brad Pitt: “ya like DAGs?”
@kojox14 күн бұрын
babe wake up, we got to watch this now
@sergodobro256913 күн бұрын
Cool video! Btw, do you use Godot or some other engine? If though, how to calculate physical interactions in seconds? Because usually it is 1 scene with fixed speed of time, and to calculate all those ai decisions everything should be sped up and without graphics
@PezzzasWork10 сағат бұрын
Thanks! I am using my own simple engine :)
@lefm_14 күн бұрын
So few nodes! Unity's ML Agents default configuration is 2 layers of 128 nodes, I dont understand why it uses so much, maybe something related to reinforced learning?
@Alayric14 күн бұрын
Double pendulum 😨
@zyro847312 күн бұрын
+1 for part 2
@BanD1t84 күн бұрын
The pendulum visualization looks really nice and tactile. Is it custom made, or was there some library/framework involved?
@PezzzasWork18 сағат бұрын
It's all custom made using C++ and SFML
@AlexanderWhillas12 күн бұрын
The random disturbances are interesting. It's a simple version of the Boston Dynamics quadruped that they kick to try and knock over and it recovers quickly. You can tell that they are using a similar algorithm to find the result, or perhaps it's the fitness function? Make you realise how they haven't gotten much further, intelligence wise from this demo. Robotics hasn't had its "Image Net" moment yet. Splendid video, love the visual description of the algorithm! Keep 'em coming man!
@julianxe8 күн бұрын
Super insightful! What tool are you using for animations?
@PezzzasWork18 сағат бұрын
I did create my own tool using C++ and SFML
@user-ns7fz5gb5p5 күн бұрын
Nice work! Is it possible that you publish this project would very interesting to read the code.
@PezzzasWork18 сағат бұрын
It is planned, I am currently cleaning the code
@bergolho13 күн бұрын
Congratulations for the video! Could you please tell me which software you use to build the animations ?
@PezzzasWork10 сағат бұрын
Thank you! I am using a C++ tool I wrote myself
@Surfingnet13 күн бұрын
Encore une super vidéo. Tu l'as codé dans quel langage ce projet? C'est quoi le cpu de la machine sur laquelle tu fais tourner le processus de sélection?
@PezzzasWork10 сағат бұрын
Merci ! J’utilise le C++ pour tous mes projets et le CPU de mon pc c’est un I7-12700K
@Gedestherosys13 күн бұрын
Can u give an example recommendation for a mobile app for this?