How to train simple AIs

[@alexislouis2320]

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

fr

[@mox189]

BASED

[@GuildOfCalamity]

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

[@bradley1995]

He did, and a cock a doodle too!

[@sebastianpohl1268]

Twist at the end: The rooster was itself an AI ...🤔

[@AA-cg1wm]

plot twist: it's a hen

[@alliepiper4772]

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!

[@thebetterbutter709]

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

[@proyoloks1386]

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

[@CraftingCat_IX]

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]

+ the balls like red things

[@the-bgrspot6997]

hyper cursed tbh

[@poultrypants]

and the balls 🤣🤣

[@sumitbiswas164]

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

[@volbla]

I like the chicken. I find it charming :>

[@knitnatsnokprogramming]

He’s alive!

[@grahamsnyder762]

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

That's actually pretty standard to alter into a categorical/discrete step.

[@TheTechnopider]

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

[@xernas7880]

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

[@Oring17]

Love your work Pezzza. You are a great inspiration.

[@notthetruedm]

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

[@mr.ditkovich9983]

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

[@teenspirit1]

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]

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)

[@Dedelblute3]

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

[@Sakejo]

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.

[@knitnatsnokprogramming]

I’ll binge-watch this rn

[@ruolbu]

how do you binge a single 13 minute video?

[@knitnatsnokprogramming]

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

[@PezzzasWork]

Amazing

[@ruolbu]

dedication

[@namdao2672]

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

[@srb2149]

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

[@karlosfy]

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

[@issamoudriss6564]

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

[@Hailfire08]

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

[@caiuschew5021]

Excellent content! Would love if you could compare a comparison between this and other RL algorithms like TD3, PPO, and SAC. Like how they would do solving the same problem

[@PezzzasWork]

Thank you! I am actually working on this :)

[@noahwinslow3252]

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

[@simon_aviation]

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

[@JayBenOh]

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

[@sourabhk2373]

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.

[@elex6934]

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

[@brickstopforall]

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

[@preguica_net]

Very nice the visual explanation

[@CyrilM68]

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

[@mnajjar85]

the visualizations are epic

[@sofia.eris.bauhaus]

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

[@quantumgaming9180]

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

[@PloverTechOfficial]

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.

[@rigbyb]

Great video! Glad to see you again

[@gedaliakoehler6992]

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

[@allanburns1190]

This will actually help me so much in my new project

[@MysteryPancake]

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

[@enderdodo9749]

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?

[@ZeroPlus707]

Great video! Hyped for the double pendulum :)

[@khatharrmalkavian3306]

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?

[@midasscheffers7610]

Awsom video, cant wait for the second part

[@P4INKiller]

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?

[@reactRiderDoughnut]

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

[@NickCombs]

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

[@DNAmaster10]

For anyone struggling in the future, this playlist, and this video specifically, was of great help for me when writing the topological sort algorithm. To be honest, I'd actually say that topologically sorting the graph is one of the hardest steps. kzbin.info/www/bejne/mXqld3ieeZxqmJY

[@o1-preview]

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

[@codedeus]

Great video as usual :D

[@kinsondigital]

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!!

[@CraftingCat_IX]

The guy is back :D

[@synterr]

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

[@lennarth.6214]

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.

[@shadowcraftersr]

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

[@PezzzasWork]

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

[@TutosIngenieria]

@@PezzzasWork I´m waiting for it everyday. Thank you.

[@BrunexGamerYT]

Could you just tell me how you manage to get smooth animations and beautiful styles in the game? Do you use any specific library to apply the styles?​@@PezzzasWork

[@motbus3]

Loved the UIs

[@Wolforce]

Great video! as always!

[@wjrasmussen666]

That is fun! Good work

[@Koroistro]

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.

[@Top10-m7r2n]

Nice work! Is it possible that you publish this project would very interesting to read the code.

[@PezzzasWork]

It is planned, I am currently cleaning the code

[@Top10-m7r2n]

@@PezzzasWorkThanks

[@Blooper1980]

Very neat video

[@abdulrahmanelawady4501]

Thank you for a great video

[@coding.emojii]

Waiting for the next one!

[@manamimnm]

That trippy music!

[@warrenhenning8064]

If you have the network exert a fixed amount of force or not in a bang-bang manner rather than getting to directly control speed (which is not very physically realistic) and don't expose the angular velocity, you'll have a harder task on your hands. In particular, without some kind of memory mechanism (recurrence, LSTMs, something like that), the network probably won't be able to solve the position-only input variant.

[@lefm_]

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?

[@ardumaniak]

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

[@Ibloop]

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

[@Gunnahan]

cant wait for part 2 🙂

[@Banaannaa]

same

[@ErikBongers]

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?

[@bradley1995]

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.

[@aymanxxxx]

Which gate logic videos you mean?

[@loicsen8003]

Very nice video, thanks for that

[@motbus3]

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

[@tatomans1982]

excelent video. I learn a lot. Do you have any video where you explain the code?

[@chris.hinsley]

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

[@geobruce1995]

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!

[@Alexander20091988]

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!

[@g3itnal]

im excited for the next video

[@happycolours8551]

Yay he's back

[@jayearl3591]

So after all these months in hiding, you've been secretly building Boston Dynamics Spot knock-offs 😂

[@ai_outline]

Hi, do you have a Computer Science background? Great video! :D

[@PezzzasWork]

Thank you! Yes I have a master degree in computer science

[@ai_outline]

@@PezzzasWork that’s amazing!!! Hope to see more great CS content like this. Keep it up 💪🏻

[@PezzzasWork]

Thank you!

[@ScienceGuides]

Great work! :-)

[@anupamdasrc6970]

this is amazing. Could you tell me what you use to do this animations/simulations?

[@theMrTortoise]

your graphics are wonderful what are you using? (Also great video im going to go play with this stuff now lol)

[@FailRaceFan]

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]

Yes I will explore other methods!

[@jazzargamer3064]

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.

[@Leonan-cx6dl]

Waiting for the next video!

[@Antcode-123]

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?

[@thatprogramer]

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?)

[@jmcglockYT]

yes he uploaded

[@marcelob.5300]

Wonderful!

[@FunkyTurtle]

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]

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.

[@vertexforger]

Great video! How are you animating the cart + pendulum as well as the visualization of the neural network as well as the graph?

[@mystifoxtech]

the double pendulum balancing problem should allow 2d movement instead of 1d to balance it because controlling 5 parameters with one output is just not feasible

[@QQ-jn5jb]

The talking chicken is amazing

[@lexxynubbers]

By the metric of calculations/time, this may be less efficient than networks that can use matrix math. However, as you are achieving so much with much fewer nodes, I wonder if this will ultimately surpass the matrix math version.

[@Radu]

Nice one!

[@PezzzasWork]

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

[@Radu]

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

[@gorlix]

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

[@MsAlfred1996]

Question: How did you create the physics simulator for the rail and the pendulum ? It looks great !

[@azuky74]

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)

[@chrisdickens4862]

Very cool!

[@QwertyIsCool]

Hes back lets go!

[@somedude5264]

4:50 I would recommend to add crossover

[@somedude5264]

which is of course not possible for this algorithm. Scrap that...