9:10 Did the audio desync in the editing phase, since it is the same audioclip from the beginning of the video? :s Then it cuts to music mid-word at 11:48

Jabril your content is extremely high quality. You make computer science interesting to a guy like me, who doesn't know anything about it

you should make another ai to automatically build harder courses any time forest completes them.

Way to call the election.

I absolutely loved this series. Thanks for making it buddy. I'm glad I'm not the only one who finds this topic fascinating.

Watching Forrest trying to run the different courses has been surprisingly mesmerizing. I'm gonna miss the little guy

Far and away the best , most in-depth (and understandable to a layman enthusiast) insight into an ML programmer's thought process that I've seen on KZfaq. Thanks!

Cheers for making this - it was a good watch! I've played with machine learning and haven't had the chance to delve into deep learning yet but this series helped visualise it better :) Keep up the good work!

sooooo good, I love how you set up these videos as entertaining and easy to follow along. heck honestly im not even doing this, but now i kinda want to. Im still going to watch the whole series today and i've subscribed. Thank you for peaking my interest again, this coming from a college student going for a Computer Science Degree.

Your Chanel got randonly suggested to me by youtube, and I was glad it was. Very entertaining to watch, and you did a vey good job at explaining the concepts behind the algorithms. A Well-deserve subscription!

I greatly underestimated how entertaining this series would be, awesome! subscribed and know to check all your other content.

Wow, that race really had me on the edge of my seat!

Found this video (and your channel) from a tweet of another programming youtuber and I absolutely love it keep up the awesome work man!

Hey Jabrils, Thank you for this great content. This is my fav channel now on :)

Dude i am NOT able to do anything with programming, somehow i came across your channel, saw this series, and must say i really really like your way of doing this. Informative and funny. keep it up!

Your level of mental energy is out of this world!! I have no words, I'm a fan now!!

I love this, thank you for sharing your knowledge and making such awsome content. This really motivates me to learn about machine learning.

Just realized I couldn't see the comment option because window was too small XD. These vidz are so dope. Clarity, content, reasoning, animation, editing, acting, music choice, dragonball reference, and overall entertainment value are 100. Thanks.

I love your videos. First off, you get to the facts in a really fun an interesting way. Your have such a great character (no pun intended, Forrest), and overall your a really cool guy. I give you my subscribe.

I think the random slice works best because it is not limited by the past results, and potentially adds new arguments that could totally work! I loved this video, you have gotten me excited about machine learning! I'm going to talk to my academic adviser about switching my major!

Hey Jabril! Awesome videos man. Keep up the good work!

Definitely my new favorite channel. You're hilarious.

Man I absolutely love this channel to bits!

I believe that even if I were not already interested on the subject, I would be after watching you dude. Loved it!

Really loving this series so far, really informative and funny too.

This is genius work. Pure knowledge. You should be writing a paper on this for a game-dev conference!!!

Just saw this series of videos on Machine learning. Very interesting and i'm enjoying them quite a bit. Just wanted to note that I think the Random % learning selection is actually the best way to mimic life.

At first I thought your videos were silly. I am a fan now. Subbed 100%. I hope you grow because you're super entertaining. Good luck!

I immediately thought of a GAN. Another network builds harder and harder courses for Forrest to try. That would be a super cool project. Lately I wonder if my life is like that. Reality is presenting me more complex problems to solve. Thank you universe for keeping me challenged !!!

Just came across your channel. Have to say that you have an interesting style of editing. Keep up the great work!

"Take a second to let that register...." 😂😂😂 I’m weak

BY FAR THE BEST IVE FOUND FOR GETTING INTO IT THE BEST

Really cool short series here. What's quite awesome is thinking about about additional methods/ways that could have been implemented to complete and make it even more efficient. For example, adding normals analysis onto the raycasts that determines the scores on the 5 directions. Getting the normals returns the directions from which the 3D faces (walls) are facing. That's, after all, the principle behind how we're able to follow a track ourselves : We see the distances and directions from restriction we're facing. Even someone who's blind uses the same principle by using his ears to analyse the direction of hard surfaces and the echos. (sounds doesn't return the same if it bounce at 90 degrees off a surface or less.)

Dude, first time watching your youtube. Hilarious brother. Thank you 😂

lol the end segment is always so funny looking after watching you talk with your mouth closed all video

just found your channel, this is top quality content keep it up!

Dude this series is amazing, would love to see some more stuff like this. also liked for ff7 music

One of best produced videos i have seen in a long while.

this man has the hand of god, I'm now blessed with machine learning.

lol it's actually strange to see him at the end of the video actually talking haha ... good job man, nice videos

I am jealous of your brain. Well done!

Dude honestly, if you don't continue to make educational videos, it will be a crime. You are amazing. Thank you

Your style is so unique! I love it

WTF 1500?! Your channel is highly underrated. You get all of my views. Thank you for vids, I love 'em

really cool stuff thanks for sharing with us

you really inspire people to learn machine learning

Love your stuff bruv!

I am super enjoying this. Awesome stuff! (I did a BSc in artificial intelligence 25 years ago - I wish I had cool tools like these to play with!)

I'm writing this out before watching the post-mortem, so forgive me if I'm saying things you already went over... I think there are a couple reasons the results weren't as good as they could have been. First, it seems like the turn radius isn't sharp enough to turn around. So when Forrest runs up to a confusing intersection he hasn't seen before, there is no way to guess whether it goes left or right. He just has to pick one, and if it's a dead-end, that simulation loses because he won't be able to turn around. However, that simulation didn't lose because it's genetically unfit -- it only lost because it was genetically predisposed to guess left at the confusing intersection. This means the automatic assumption by the computer is that he was genetically unfit for any race in general, but really he was just guessing that the intersection turned left. In fact, that could have been the best Gump yet, but lost because he rolled the dice wrong. Second, piggybacking off that first point, the A.I. may just be training by memorizing the track. Who knows if it's actually learning how to navigate new areas? All it knows is the specific track. Every time you train it on a new track, it is going to fail in the beginning and then have to readjust to the new track as it memorizes the new one and forgets the old. Ideally, I think, the best way to train it would be to 1) Give it a sharp turn radius, and 2) Randomly generate a new track for every generation. That way, it has to rely on its ability to adapt 100% and not at all on its ability to remember tracks. Of course, then it would be hard to reward it properly for advancing in the track so 3) You'd have to give it an incentive for getting closer to the end goal... maybe draw an A* path to the end and make the distance inverse to the score.

6:55 that is some risky stuff my friend, and I like that way of thinking

6:44 dat explanation of random crossover function, lolol.

I'd love to see Forrest run on a course that has some dead ends, and also some that have shortcuts 😊

What software do you use to animate your videos? p.s. this is a sick video series!

I love the progress that you made with this project. I have a few helpful suggestions that may work to help you. First, I think you would need to train Forest to run both ways. Second, you will have to store the information of what forest learnt (in a database of some type) from previous course that he ran so he can apply the knowledge that he learnt for his new course that he's about to run. Hope you see my logic.

That ff7 music though

Awesome series!

Cool video. Like your style. Really good content !!!!

6:53 I removed my upvote just to give it again.

Really enjoyed this series :)

FYI. I came to your channel through mark rober's!! And I am glad:)

Soooo could this be applied to my lawn mower so it'll cut my grass for me?!

edge of my seat! very entertaining.

🎵This score though, you are awesome bro

I really liked that part at the end where we got to see you move your mouth! I know its weird but it just feels so much better to see your mouth move than not..... :P great videos btw

Episode 2: Don't talk to me about politics. Episode 3: Brings up politics.

I love this, I never thought of making a neural network AI for my game and now I am excited. You make it easy and fun to learn this hard topic and I appreciate it, sub for life. I look forward to more of your videos like this or programming in general. I may have missed it but what language are you using, C++, Python, C#. I dont watch the video completely before I comment just to give you a heads up so if this question is answered I will edit this comment. I am so excited, its crazy I never thought I would be this way about Neural Networks, I know you must think I am crazy but it was like BOOOM!!! my mind expanded and I saw so many things to do with this. Keep up the great work. I look forward again to more.

When it comes to crossover, if crossover is performed on the whole population it will effectively make them all "the same species". Every time two networks with different strategies are mated, it is almost certainly going to result in failure (nonviable offspring), so the resulting "species" all work the same so their pieces are interchangeable with slight variation. That is highly consistent with what you are seeing. I see a lot more success in simulations I've ran when I allow speciation to happen if I am using crossover or if I allow species to have "crossover points" that allow them to crossover at some points if it matches with the one being mated with. However, in your case it seems that since there is just one solution to this problem that only one species was required anyways, so it made more sense to just make the whole population quickly be that.

This is amazing!

The link to part 2 in the description actually links to part 1. Also it would be nice if the description had the link to the next video. Or make video end cards, because KZfaq doesn't always recommend the next video and people are not always watching the playlist. That increases views and watch time and retention.

This guys is a Damn Genius!

I dont know how hard it would be be But would a memory space for forest been good for him. Like what ever works the best is saved and have a reward system for exporing? I dont know just asking

I couldn’t complete that course that many times with out touching the walls damn, Go Forrest!!! Lol

I don't like whoppers, but love this ml experiment. Thanks Jabrils!

This is the first time i hear about these stuff but i think if u put a timer on forest ghosts(i call them that) and reward the one who runs the course in less amount of time it can be trained better! i luv the way u make these Videos keep up to good work :) Peace

That plant bit got me :')

how'd you make those beautiful graphs? and what program do you use to train forest?

Hi. I'm interested in what programming software you used as I'm planning on making a neural network for my A-Level Project and I can't think of anything better than C# or python (python I've never used before). Thanks

Could you give some advice about how you got from, wanting to program too making A.I. like where to started and the steps afterwards. I see a bunch of videos and bootcamps but none of them tell what I should learn first they are all about what they are selling.

You explain it so much better damn !

For 'the day avg of 5 session avg' is there a benefit to separating trainings in 5 sessions per day then trainings per day if it's going to be averaged altogether anyway?

Amazing Video and Quality :D

can't stop WATCHING!!!

Arrgh! I was at the edge of my seat! why, forest?! I'm hoping there'll be a "forest 2: spawn of forest"

See how you get around the whole decision making for random or precise functions is using your random function as a optimization side loader that runs a real-time micro SIM of the scenario going on using its top performing data and communicating it back to the precise function that operates the main character or scenario. And what you'll see in the graph is an exponential rise in performance basically you're giving me AI the ability to self-simulate and communicate the best data to the motor control function

Incredible bro

First of all, very nice series, you got yourself one more sub! Some questions: I might have missed it, but did you apply any mutation to your genetic algo? If not, that might be why a riskier one is better, as in nature mutation is the way to get out of local minima. Why only use one layer in your neural net? It would be interesting to compare performance of a few Forests with different number of layers. Maybe the model is a bit harsh. Forest can only run left or right. If he also knew how to stop, but was rewarded for running a course fast, then I think he would do better. As it stands I think he can enter a dead end which he can't see the end of and thus have no chance to turn back, regardless how smart he is. Once again, had a lot of fun watching the series, hope to see more game related ML!

Was I the only one who got too excited to see him talking straight to the camera?

dont know if you mentioned it but an age old strategy to visit a labyrinth ( which i used in Wolfenstein ) is to go forth, keeping the right ( or left ) hand on the wall

Nature easily marries with your data suggesting processes with randomized values are the most efficient methods of learning. Consider that genetic mutation is practically random - it's not that a species will intelligently adapt to environmental factors, but rather those which develop advantageous traits due to random genetic mutations are more likely to survive and thus pass on the new characteristics. Conceptually it's near identical to your randomized processes recieving priority values, favoring efficient processes and passing the data to the next function. It is interesting all the same that these processes would be so much more efficient when compared to processes that had intelligent guidance.

Great Content!!!!

Love your videos, found them today! Amazing editing work, i have been doing some movie and sfx work in school, but this is just amazing to watch! A bit inconsistent about politics though, and maybe a little over simplified. That last point might bring in more viewers, though.

Love these videos, man. Your explanations and sense of humor make this kind of information fun and easily digestible. What aren't fun and easily digestible are Whoppers. Dude. Whoppers are trash. Keep it up!

How did you make the hex courses? Is it in unity? Or something else?

This series is so awesome. Do you think I'd be able to implement a similar environment for my end of the year project to build a robot that can get through any cardboard maze?

one likely reason for natures adaptation of the slice crossover is that nucleic acids aren't single input values, they come in triplets called codones that correspond with amino acids for protein building. Because of the length of polypeptides, switching a single nucleic acid could have monumental consequences, like accidentally making tons of stop codones which says to stop the polypeptide construction after tens of amino acids for proteins that would normally be hundreds or thousands long

"Nature just needed more time" Nature isn't going to get the blood vessels out of the way of my actual light receptors in my eyeballs!

Love this series. (and love the nod's to FF7) :) you are awesome.

What do you use to create the courses?

What software did u use for generating his course....?

What computer hardware are you using?