Nice video my friend. I would stay around for the seconds parts guys, exciting things ahead ;)

26 күн бұрын

fr

@mox189

18 күн бұрын

BASED

I could be insane, but I would swear that a rooster just taught me AI.

@bradley1995

Ай бұрын

He did, and a cock a doodle too!

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.

@plaintext7288

Ай бұрын

+ the balls like red things

@the-bgrspot6997

Ай бұрын

hyper cursed tbh

@poultrypants

Ай бұрын

and the balls 🤣🤣

@sumitbiswas164

Ай бұрын

Extremely distracting! I would prefer relevant scenes in a serious video.

@volbla

Ай бұрын

I like the chicken. I find it charming :>

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!

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.

He’s alive!

From a frenchmen to another, your accent has improved so much! Your videos are captivating as always.

@proyoloks1386

Ай бұрын

yeah it's insane, I almost forgot that this is the same guy as 8 months ago...

Now build entire ecosystem with Darwin's evolution principles.

@Maus_Indahaus

Ай бұрын

I'd like to see that!

@SystemBD

Ай 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-0063

Ай бұрын

@@SystemBDNot hard to code is an understatement. In my opinion, its probably the easiest to code from scratch…

@allanburns1190

Ай бұрын

I am actually working on something similar

@TVDaJa

Ай 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

Can't wait to see your next video 🙌🏾🙌🏾

Love your work Pezzza. You are a great inspiration.

Extremely excited for the next video! For some reason, AI training videos just scratch a certain itch so nicely

Finally ! I just love your content, i'm happy to see you again, also on my favorite topic

The first steps are always the hardest, so it might be good to show some actual code examples for them.

I’ll binge-watch this rn

@ruolbu

Ай бұрын

how do you binge a single 13 minute video?

@knitnatsnokprogramming

Ай бұрын

@@ruolbu By rewatching it over and over again at 0.25x speed

@PezzzasWork

Ай бұрын

Amazing

@ruolbu

24 күн бұрын

dedication

I love how you animated this! It looks so cool and made it easy to follow along

I was literally about to work on a project of mine that requires AI, immaculate timing pezzza

I love this channel. It's enjoyable to just watch cool coding stuff.

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?

Love your videos and can't wait for the next one!

I love your videos ❤ ai is such an interesting topic and I'll watch part2 as soon as possible

This video is super nice man, waitin for the second part!

Really inspiring. Will be waiting to see the code! Great content :)

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.

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.

Great video! Glad to see you again

Your projects are amazing, and often very beautiful. I aspire to make software as good as this one day!

The guy is back :D

Great video! It's a very nice visual representation ... that must have been a ton of work!

im trying to learn ML and DL by myself and find this super helpful, waiting for your next masterpiece

Thank you SOOOO MUCH!!!! I always wanted to do something like this, this will really help!!!

This will actually help me so much in my new project

That is fun! Good work

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.

Great video! as always!

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?

Very nice video, thanks for that

I was wanting a video on machine learning!! It's from you aswell!

Great video! Hyped for the double pendulum :)

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.

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!!

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?

Awsom video, cant wait for the second part

Very neat (haha)! Also great classical controls problem!

Hurry up with the second part, I can't wait!

Loved the UIs

Great video as usual :D

inverted double pendulum sounds intense! looking forward to it. :)

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.

@Prism019

5 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)

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!

I can't wait to see what happens next with the double pendulum !

nice! it reminds me of the MarI/O video, it uses this algorithm too

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

soooo, now I want to watch the next video, it is so excited

Thank you for a great video

Very neat video

Waiting for the next video!

Waiting for the next one!

Wonderful!

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

Great work! :-)

That trippy music!

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?)

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 😄

@PezzzasWork

25 күн 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.

That's an awesome video. Crazy good graphics! Mind giving us a hint on how you made them?

@PezzzasWork

25 күн бұрын

Thank you! I am using C++ and SFML, I will probably make a series of small tutorial to explain how I do this

amazing work and i hope mine will work

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.

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!

im excited for the next video

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

Yay he's back

I'm still curious about the UIs :) anxiously waiting for the source code ❤

Very cool!

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.

Hes back lets go!

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?

YES :D

So cool example! Can't wait to see how AI will handle chaotic pendulum ;)

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.

Was nice to see a none layered net ! But just a DAG net.

Nice one!

@PezzzasWork

24 күн бұрын

Thank you! I am really impressed by your understand ai videos

@Radu

13 күн бұрын

@@PezzzasWork you've seen those? Cool, thanks for watching :-)

Super insightful! What tool are you using for animations?

@PezzzasWork

25 күн бұрын

I did create my own tool using C++ and SFML

Congratulations for the video! Could you please tell me which software you use to build the animations ?

@PezzzasWork

25 күн бұрын

Thank you! I am using a C++ tool I wrote myself

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)

The pendulum visualization looks really nice and tactile. Is it custom made, or was there some library/framework involved?

@PezzzasWork

25 күн бұрын

It's all custom made using C++ and SFML

I feel like I've learned more in this video than in 5 hours of reading. Will you also talk about other learning algorithms?

@PezzzasWork

25 күн бұрын

Yes I will explore other methods!

yes he uploaded

cant wait for part 2 🙂

@Banaannaa

Ай бұрын

same

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!

The talking chicken is amazing

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?

@PezzzasWork

25 күн бұрын

Merci ! J’utilise le C++ pour tous mes projets et le CPU de mon pc c’est un I7-12700K

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?

What a hook!

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

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

@PezzzasWork

25 күн бұрын

Thanks! I am using my own simple engine :)

im exited to see it with a double pendulum

How did you implement the visualization? It looks very nice. Thanks!

@PezzzasWork

25 күн бұрын

I am using C++ and SFML, I will create a series of tutorials to explain how I did as I have quite a lot of questions about it.

Yeah.. the talking cockerel with sunglasses talking about NN is weirding me out.. Great video!

how does the NEAT method you use use the reward function to optimise the network? Is that is a feature inherent to the NEAR method, or is it relying on extra work?

@PezzzasWork

25 күн бұрын

My implementation is a simplification of neat but the global principle is the same and the reward function is just there to drive the random operations toward better solutions by introducing a biais for better agents, at the core of the algorithm there almost only random things happening.

Do you have any extra channels where you teach these AI programs?

Are the mutations equally distributed between those 4 possibilities? But some extra mutation decisions need to be made: where to insert a new node, which weight to change or where to add a new connection. Are these decisions also equally distributed?