How to train simple AIs
Вставка
- Опубліковано 27 тра 2024
- 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. - Наука та технологія
Nice video my friend. I would stay around for the seconds parts guys, exciting things ahead ;)
fr
BASED
I could be insane, but I would swear that a rooster just taught me AI.
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.
+ the balls like red things
hyper cursed tbh
and the balls 🤣🤣
Extremely distracting! I would prefer relevant scenes in a serious video.
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
That's actually pretty standard to alter into a categorical/discrete step.
He’s alive!
Now build entire ecosystem with Darwin's evolution principles.
I'd like to see that!
That is actually a branch of classical AI called Evolutionary/Genetic Algorithms. They are not hard to code, but they have limited applications.
@@SystemBDNot hard to code is an understatement. In my opinion, its probably the easiest to code from scratch…
I am actually working on something similar
@@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
From a frenchmen to another, your accent has improved so much! Your videos are captivating as always.
yeah it's insane, I almost forgot that this is the same guy as 8 months ago...
I’ll binge-watch this rn
how do you binge a single 13 minute video?
@@ruolbu By rewatching it over and over again at 0.25x speed
Amazing
dedication
The first steps are always the hardest, so it might be good to show some actual code examples for them.
Can't wait to see your next video 🙌🏾🙌🏾
Love your work Pezzza. You are a great inspiration.
Finally ! I just love your content, i'm happy to see you again, also on my favorite topic
I love how you animated this! It looks so cool and made it easy to follow along
Extremely excited for the next video! For some reason, AI training videos just scratch a certain itch so nicely
Love your videos and can't wait for the next one!
I love this channel. It's enjoyable to just watch cool coding stuff.
I was literally about to work on a project of mine that requires AI, immaculate timing pezzza
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.
I love your videos ❤ ai is such an interesting topic and I'll watch part2 as soon as possible
Really inspiring. Will be waiting to see the code! Great content :)
This video is super nice man, waitin for the second part!
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.
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.
Great video! It's a very nice visual representation ... that must have been a ton of work!
Thank you SOOOO MUCH!!!! I always wanted to do something like this, this will really help!!!
Your projects are amazing, and often very beautiful. I aspire to make software as good as this one day!
im trying to learn ML and DL by myself and find this super helpful, waiting for your next masterpiece
Great video! Glad to see you again
I was wanting a video on machine learning!! It's from you aswell!
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?
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! Hyped for the double pendulum :)
This will actually help me so much in my new project
Hurry up with the second part, I can't wait!
Thank you for a great video
Very nice video, thanks for that
Great video! as always!
Awsom video, cant wait for the second part
inverted double pendulum sounds intense! looking forward to it. :)
Great video as usual :D
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
I can't wait to see what happens next with the double pendulum !
Loved the UIs
nice! it reminds me of the MarI/O video, it uses this algorithm too
That is fun! Good work
soooo, now I want to watch the next video, it is so excited
Waiting for the next one!
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
Very neat (haha)! Also great classical controls problem!
Great work! :-)
Very neat video
That trippy music!
The guy is back :D
Waiting for the next video!
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.
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
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!
amazing work and i hope mine will work
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?)
I'm still curious about the UIs :) anxiously waiting for the source code ❤
Wonderful!
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 😄
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.
So cool example! Can't wait to see how AI will handle chaotic pendulum ;)
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.
Very cool!
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?
im excited for the next video
That's an awesome video. Crazy good graphics! Mind giving us a hint on how you made them?
Thank you! I am using C++ and SFML, I will probably make a series of small tutorial to explain how I do this
Yay he's back
Hes back lets go!
The talking chicken is amazing
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!
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?
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.
Super insightful! What tool are you using for animations?
I did create my own tool using C++ and SFML
yes he uploaded
Congratulations for the video! Could you please tell me which software you use to build the animations ?
Thank you! I am using a C++ tool I wrote myself
cant wait for part 2 🙂
same
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
I feel like I've learned more in this video than in 5 hours of reading. Will you also talk about other learning algorithms?
Yes I will explore other methods!
Yeah.. the talking cockerel with sunglasses talking about NN is weirding me out.. Great video!
Was nice to see a none layered net ! But just a DAG net.
How did you implement the visualization? It looks very nice. Thanks!
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.
So after all these months in hiding, you've been secretly building Boston Dynamics Spot knock-offs 😂
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?
Merci ! J’utilise le C++ pour tous mes projets et le CPU de mon pc c’est un I7-12700K
The pendulum visualization looks really nice and tactile. Is it custom made, or was there some library/framework involved?
It's all custom made using C++ and SFML
Nice work! Is it possible that you publish this project would very interesting to read the code.
It is planned, I am currently cleaning the code
@@PezzzasWorkThanks
Nice one!
Thank you! I am really impressed by your understand ai videos
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
im exited to see it with a double pendulum
What is the best compiler for a code made in Scratch?
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)
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!
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
Thanks! I am using my own simple engine :)
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!
Talking chicken? I'm in!
Do you use any 3rd party library over SFML (for drawing charts, parts or so) or this is your own implementation?
I just use SFML, all the charts are made with it.
+1 for part 2
YES :D