Congratulations for the video! Could you please tell me which software you use to build the animations ?
@alliepiper47727 годин тому
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!
@twenty944707 годин тому
Predator do not eat if they are not hungry (>80% energy) Prey need to eat too, add vegetable on the Map, If they are low prey, predator should start to cultivate them
@kyuuaditya7 годин тому
dont make us wait another year
@RenCode8 годин тому
boobs physics ❌ balls physics ✅
@dwarf_chicken45048 годин тому
oh crap
@higuy34828 годин тому
connect the movement ai with the prey vs predator ai, i think that would look fun
@midasscheffers76108 годин тому
Awsom video, cant wait for the second part
@Marco-kl7ds9 годин тому
hi.
@christianpayne68269 годин тому
Absolute chillest gig I've watched
@Gedestherosys9 годин тому
Can u give an example recommendation for a mobile app for this?
@sergodobro25699 годин тому
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
@filippo73499 годин тому
Do you use any 3rd party library over SFML (for drawing charts, parts or so) or this is your own implementation?
@Stagnated54110 годин тому
What is the best compiler for a code made in Scratch?
@blackhole3710 годин тому
mesmerizing.
@JoseFerreira-un2cl10 годин тому
What did you use to make the animations?
@JayBenOh10 годин тому
Great video! It's a very nice visual representation ... that must have been a ton of work!
@Alexander2009198811 годин тому
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!
@ardumaniak11 годин тому
Hurry up with the second part, I can't wait!
@sergiomanuel220612 годин тому
Do you share the code to create all the test cases ands animation?
@thebetterbutter70912 годин тому
From a frenchmen to another, your accent has improved so much! Your videos are captivating as always.
@Blooper198013 годин тому
Very neat video
@termisher567613 годин тому
Oh 1 and 4 doff is one is pulling and other is pushing itself
@alessi424913 годин тому
Yeah.. the talking cockerel with sunglasses talking about NN is weirding me out.. Great video!
@0ctothorp14 годин тому
okay so I don't exactly like the talking chicken, it's distracting from what you're actually saying.
@teenspirit114 годин тому
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.
@MysteryPancake16 годин тому
nice! it reminds me of the MarI/O video, it uses this algorithm too
@dubfather52118 годин тому
yo i made this in javascript its called mentisjs
@srb976720 годин тому
Your projects are amazing, and often very beautiful. I aspire to make software as good as this one day!
@lennarth.621420 годин тому
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.
@Deachuu20 годин тому
why is it that most youtubers that make "ai learns how to walk run..." using this method just feel like the ai makes every mistake possible to later avoid them, and if one very minor thing changes in the ai character (leg lenght, weight..) or in its environment, (stairs changing sides, extra cube..) they have to relearn every thing like a newborn instead of keeping the knowledge of how to walk
@Joorin471119 годин тому
The domain is much bigger for "training an AI to walk" with many more inputs and outputs and, typically, an enormous amount of valid states for the network to learn.
@QwertyIsCool21 годину тому
Im confused when you say weight modification. How do you decide how to change it?
@Joorin471119 годин тому
Typically, it's done with a random change bounded to a small interval.
@Source-dy2ed22 години тому
This man is creating the cure for cancer
@iaadsi22 години тому
Stanley02 is what got me into ML and computer science in general. NEAT is fantastic, extensible, tolerant, lots of fun, and the paper itself is good reading too.
@v037_22 години тому
oh my God a talking cock
@yraharchenko636423 години тому
soooo, now I want to watch the next video, it is so excited
@GuildOfCalamity23 години тому
I could be insane, but I would swear that a rooster just taught me AI.
@QQ-jn5jb23 години тому
The talking chicken is amazing
@GabeSullice23 години тому
Love your videos... But... Didn't you used to be french lol 😂
@allanburns1190День тому
This will actually help me so much in my new project
@AannoonnnnДень тому
G ❤️🔥
@isg9106День тому
I’m ai, and there’s no way for you to tell if it’s true or not… 🤖
@nemonomen334023 години тому
How many buses do you see? 🚘🏍️🚦🚌🚕🚌🚓
@DalrocДень тому
Calculating outgoing connections and adding them to the target node? Why not do a weighted sum of the incoming connections?
@Joorin471119 годин тому
Doing it this way serializes the changes and, if I were to guess, just fits well with the DAG implementation.
@gta5onlineshortsДень тому
I didn't see any writing on scratch
@synterrДень тому
So cool example! Can't wait to see how AI will handle chaotic pendulum ;)
@dedelblute3946День тому
I love this channel. It's enjoyable to just watch cool coding stuff.
@alexislouis2320День тому
Nice video my friend. I would stay around for the seconds parts guys, exciting things ahead ;)
@ryshaskДень тому
Talking chicken? I'm in!
@grahamsnyder762День тому
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