AI Teaches Itself to Play Flappy Bird - Using NEAT Python!

[@TechWithTim]

Hope you guys enjoyed the video! Just wanted to mention again that a lot of aspects of the NEAT algorithm were left out of this video. I wanted to make the examples as simple as possible to ensure even the beginners had an idea whats going on. If you want to learn more about it consider reading this paper: nn.cs.utexas.edu/downloads/papers/stanley.ec02.pdf . Finally, if you like this kind of video and want to see more let me know!

[@ishansharma1511]

It's amazing how simply you explained it!

[@cruiseengineer]

can you please do this project like you explained pygame tutorial..?

[@Stinosko]

It's very NEAT explained 😄 I love this way of teaching 😁

[@tahabouziane9560]

Definitely like this kind of videos ! can you make tutorials with more details ? keep it up dude (y)

[@lamkuen]

I've been looking for NEAT explanation and yours is the most easy to understand. Thanks so much! I guess NEAT is a very promising AI algorithm for developing general AI. Isn't it? Also, could your code run on Google Colaboratory or it needs some fine-tuning. Thanks!

[@mihirsampat7624]

Loved the way you taught this entire tutorial. You taught in such a simple method, Really appreciate your efforts man! Looking forward to more tutorials!

[@calebarulandu3068]

Great Video Tim! I think that making a step-by-step tutorial on NEAT or maybe even doing this project from scratch would be really helpful. It would probably take a good chunk of time, but I think it would be really useful.

[@ANEEQHKHAN]

Amazing video! As a DevOps engineer with python knowledge I feel this video is extremely valuable for me. Thank you for sharing this!

[@ianselley2725]

Love this style of video!! Keep doing whatever you want to do. You'll always do it great!!

[@moejoe1996]

It is really nice how you explain things, i've seen this AI in other channels but didn't understand them. But when you do, I understand EVERYTHING! thanks Tim!

[@rakshithyadhav7274]

The way you teach is really good. Hope to get more of ML and AI stuff from the channel . Thanks 👍

[@pranavshridhar452]

Excellent stuff. Keep up the great work buddy.

[@armandtvanzyl4544]

DUDE! I just really want to thank you, you've made my life and my journey SOO much easier, and your really inspiring me to do amazing things. You are one of the best teachers I've ever seen!

[@devendradesai1597]

Love the channel.. looking forward for a tutorial for the above project..😊

[@caeestevao]

Yes! Would love to Watch him teaching the code details

[@draker67]

Wow, this is just awesome. Code bullet's videos are pure entertainment Yours is worth a gazillion more from a learning perspective. Plus I actually find this very entertaining too.

[@pratyushtripathy2750]

Nice video Tim. Would be great to try on own. Thanks much! Keep posting!

[@novicetech1]

Absolutely love this approach. Please do more like this. You make really complex subject easier to understand and digest. Thanks.

[@PH_SPO]

Guy, first time here. Excellent explanation on the topic. Great job!

[@Nick-jb9jn]

This was a fantastic introduction to AI and how NEAT works. I would love to see more videos about using NEAT in different games in the future. I found your channel a few days ago and instantly subbed, your content is well structured and easy to follow. I look forward to watching more of your videos. Keep up the great work!

[@TechWithTim]

Thanks Nick! Really appreciate that :)

[@kenchang3456]

YES, I definitely agree with the style you used to explain this subject. And if you can do a NLP video series I would really appreciate it.

[@user-rg2rd1kn6s]

It was super easy to understand Thank you for this vid. You kinda saved my life. I used your explanation on NEAT for my school project and added your link to it. It's not a big project just a small presentation but still you're a life savior.

[@fadop3156]

You always upload the videos i need

[@parsahosseini4241]

Hey Tim, I beg you to do a machine learning and deep learning tutorial, all the resources and tutorials on internet are either too old or too complicated, but your teaching style... it's just amazing, and it's not just me, I'm sure many people would love a machine learning tutorial from you, you made this concept so easy to understand that I'm sure I wouldn't get it if I were watching another machine learning tutorial on udemy or coursera!, I will be soooooo happy if i hear that you're working on a machine learning tutorial. Thanks a lot for your free content man. PS: like the comment to show Tim that we want him a machine learning tutorial 😄😄😄

[@TechWithTim]

Guess what?! I have one already! On both machine learning and deep learning

[@parsahosseini4241]

@@TechWithTim Yeah! I haven't been on KZbin for about 3 months and you've published so many new content that I'm gonna watch them all! Love it😍 Thanks a lot, and.... my bad for not being aware of your videos. BTW, just another question, are going to explain the different types of neural networks? I don't know them but a heard some of their names, like recurrent neural networks and others? I'm gonna check your deep learning playlist every day😄 THANKS A LOTTTTTT!

[@abeechr]

Outstanding! I’d love to see more!

[@RRKS_TF]

I would honestly love to see a series on how you got to this point

[@adarshsingh764]

Code bullet is more entertaining than informative, i like this better. EDIT: it's almost the same, but less enjoyable

[@abhyudayaagarwal589]

I know i am late but please make every video u make like this one. Mind blowing

[@RandomShowerThoughts]

Definitely make a tutorial on this! This is way too interesting of a topic

[@Finn-jp6pn]

Really enjoyed this. I'd love to see more ML content on your channel.

[@jahnavithota1949]

Hey Tim, Your tutorial series is amazing! Learnt a lot. Continue making more and more tutorials!!

[@anakinskywalkerrr]

Finally, games and AI. The two most interesting thing in programming

[@playerscience]

Yes Yes!!! Completely Agreed 💯👍👍👍

[@ishansharma1511]

This is something new for me and I liked it. Make more videos of this type!! Thank you!!

[@redapple0007]

your video and new style was so good. Keep it up!!

[@purnenduroy8796]

That was awesome.. Need to see more of your videos

[@michealhall7776]

Yes, some of your other videos are boring but this is a really good style. Well prepared. Looking forward to the next lesson in the series showing how to make this ourselfs

[@williamikennanwosu]

Good effort Tim, well done!

[@schogaia]

Random comment for the KZbin algorithm to rank your video better

[@TechWithTim]

Appreciate it!

[@schogaia]

@@TechWithTim what I didn't add: I really enjoy this series - I started with python 6 months ago and you explain everything really well. Thank you!

[@sotospeak6741]

one of the only good explaination channels iv seen

[@xxalienxx9541]

I though it would look complicated but you explaines it really great.

[@alan-alan-]

This video is awesome. Thanks Tim for all your content. Keep going!

[@Zanecronium]

New sub this was so helpful I have never seen someone explain it in a way i can understand AND give code AND like a source thank you so much! Edit: AND THE MODULER????

[@antiRuka]

Best explanation on the net so far!

[@rutvikrana512]

You should do this kinda intro videos ... it will bring us to your playlist 💕💕💕

[@peterm9893]

Tim, you sir deserve a LOVE not just a like. Thanks man you're a genius, and I've learned a lot from you. Keep Going bro !!!

[@harshdeeptelang127]

Thanks bro! i genuinely appreciate your hard work on this video!

[@Mark-lp9ke]

Cant wait for the project tutorial! 😍

[@TechWithTim]

It’s out!

[@sautante]

This video was so good, please make more! :D

[@mayurchavhan8590]

Excellent explanation on AI using a simple example, No Wonder Microsoft hired you. Keep up the great work. Love from India

[@pampam6622]

Thank you Tim, i really enjoy learning python by watching your videos!

[@黃冠綸-t5i]

Thanks a lot for sharing flappy bird programming lines in detail. Your vid is of great help to my project.

[@21abdullah89]

Awsome Man. I would recommend as Ai is getting more and more popular espacially even in game so at least upload a video here and there on more games and Al implementing on that game.. As always Great effort man and great work

[@ChristianZenker]

Thanks for this Video. Currently im working throug your pythong Videos (my target is a own written AI ^^ ) and currently youre (for me) the best python and python (pygame/ai) teacher. Thanks for making this videos :-)

[@RandomShowerThoughts]

Amazing. I’ve always wondered how this was done.

[@zach-7102]

Incredibly helpful, thanks so much

[@rynexakil7443]

thx for the video , i was hoping that it's more than one Perceptron connection ...... i think that if you put a victor or a ray from the eye's and let it see as it's go's up and down where the gap is, it will be smarter rather than given it where the gap is. thanks again

[@frankmessina7475]

I am going to try to make this as well, thanks for the info. I would love to see a video of how you went about coding it.

[@DevendraSingh-jt8qj]

good job man! post more to learn

[@SuperArinc]

More game creating videos please! 😄

[@idatewang6205]

Great video! Definitely hoping to see more of those😃

[@arbazkhan8320]

Really great video tim please make more videos like this

Very clear. Well done! Best video on this topic. Thanks.

[@AgentRex42]

Can't wait to see your tutorial if you will make it ! ;)

[@TechWithTim]

Tutorial has been made

[@AgentRex42]

@@TechWithTim Oh, ok !

[@patloeber]

Nice Video!

[@ishaangupta6572]

Nice video man

[@usmanbinabdurrasheed5949]

You are simply awesome!!!

[@minindusheheran6624]

Explained really well :) :) Thankyou..!

[@novicephiladelphia.d4788]

OMG that's what I really want to learn. Using AI to play games wow. look forward to your tutorial about this and other methods to make ai to play different games like capturing the frame and analyse👍👍

[@emilievaneps8858]

Nice video! Thanks!

[@Sanyapantyukhin13]

Tim, thank you for such great vids!

[@marco.nascimento]

Nice video, very entertaining and informative at the same time

[@shardulsilswal1140]

Thank you for explaining so clearly. I am gonna try this on my own now.

[@sirwilliamhenry]

Awesome content, man! U the best!

[@tigruhh588]

Great video!

[@ishaankalsi]

I love how you presented! Would try to replicate in my workshops.

[@neilleonard5781]

Great video! Some of the other NEAT based projects don't share their code, so I am excited to get my hands dirty. Is this an open source project that is interested in Pull Requests? Either way thanks for the video!

[@TechWithTim]

Ya for sure! Send the pull requests :)

[@zackhoudache9539]

goooood joob u have a good sense of teaching keep doing these video all the best

[@pranavkarthikeyan783]

Keep up the great work!

[@raymarkdelpuerto9094]

love this one!

[@wesleyteenwesley]

Amazing content, simple and beautiful explanation

[@user-tz3di7he8f]

Honestly, you explained it amazing

[@MatrixVor]

Amazing video. I'm curious about what made you pick "> than 0.5" as a threshold to jump? Could it be 0 or any other numbers (like -0.5 or -0.7). Thank you so much.

[@alexanderhuliakov6012]

Wow, one of best "begginer" videos about neural networks.

[@vulturebeast]

Really awesome, subscribed. 🥂👍

[@stonez56]

Great video, Tim! I just subscribed this channel. Could you do a tutorial on car licensing plate recognition, both on video and still images. Thanks!

[@DAJakaRedAries]

Gonna try this on my own. Thanks!

[@thecoone2797]

So in the beginning you give random weights for the starter population right. But in what range do you choose those starter weights? Also, usually when i see video's like this one there is also a hidden layer in the network. What is the benefit of that hidden layer, if it works without one like you did? EDIT: i tried using starter weights and bias of random value between -0.5 and 0.5, but the birds didn't learn anything. I dont really know if i should do something with my distances before passing them to the weighted sum? I get like random values of -200 to 200 for distances

[@maedre4966]

good job thank you for sharing codes

[@yes.0]

Very Good work done

[@bopynyt640]

Great video! I’ve never programmed and I’m 17 but recently I’ve gained interest, especially in AI and ML. What would you recommend to learn these things that start at the most fundamental level because i learn best that way.

[@TechWithTim]

Well I do have a course of fundamental programming with python

[@brute505]

keep doing this style

[@JosePerez-qt8cf]

Excellent vídeo and explanation I would like more vídeos of ML and DL Thanks a lot

[@sontref]

Correct me if I'm wrong. To implement stuff like that, you must code your own version of game? And if so, is it possible to teach NN to play some complex games?

[@TechWithTim]

Not necessarily, you can use computer vision.

[@pawelpawelec1419]

Yeah I want more! :D

[@exa4564]

I liked the style of the video, but some code-example would have helped to understand how to implement NEAT into a game

[@khalilj.9051]

Hi Tim I wonder if this NEAT-python AI-programming adaptable for numbers and statistic, able to find patterns in massive data of numbers and combinations? Thanks a lot for your great content..

[@Capitalust]

This was dope af

[@technical_research_hacks]

I'm mechanical engineer but I'm just curious about how it works.... Good work bro

[@XxNinjaLimeXX]

As someone who has learned a bit of python for work even though it's outside my field, but has become interested in machine learning this is really fantastic. ML is super interesting to me and NEAT is wild. I've run the source code and it feels like magic so I've really gotta dive in and try to get a handle on whats going on. Classes are still something I'm not confident with lol. You've certainly earned a like and a subscriber though. Thank you for the video.

[@AlamKhan-yt9wd]

Great explanation

[@AgentRex42]

Great ! ;)

[@andrey1652]

Can you please explain how do i find out the value of the activation. in this case 0.5 Thanks!

[@sashamuller9743]

did you manage to get it?

[@lautarodapin]

Excellent!

[@Pythonenthusiast]

I am just thinking out loud, would it be possible to have this work with knowing only the position of the bottom pipe and the bird y position? I guess that we can base the jump/not jump decision, based on those 2.

[@SofieSimp]

Can you tell me why you chose TanH instead of Sigmoid activation function?