59

I JUST FINISHED MY FIRST NEURAL NETWORK!!!

But first of all, as I know you guys, it's spaghetti code and even I as a newb see places where I used too few-dimensional array or passed useless parameters or simply wrote too many redundant lines of code. I know it. I will make it MUCH better next time. Period.

But OMFG this made me scream from happiness today!! Just these few seemingly random numbers... I'm really done.. That's why I jumped into coding year or two ago..

And for some background, I didn't study any IT school, I'm just highschooler (general grammar school) who traded gaming for learning. Also my maths teacher teached NNs on university and is very keen to teach me, so that's that.

Now I wanna make the best out of it and I'm looking forward to write some well documented and flexible library, parallelized and everything (I'm gonna learn a lot in the process of doing this) better then FANN.

Maybe I'm gonna fail(99% probability but hey, I'm programmer beginner, I still think I can code everything I want). But if there is just one moment like when I saw this screen today, I'mma trade my life for it.

Sorry for taking your time guys, I was just genuinely stunned... A lot

Comments
  • 15
    Btw start using Visual Studio. Its much better than codeblocks
  • 4
    @Binary Can confirm.
  • 2
  • 2
    @Binary Am gonna do that for the next one! I was always just scared of how robust it is and how many things one must do in order to use it.
    It just feels like an extreme overhead when one just wants C and GDB (or something similar) 😂
  • 2
    I remember following a code project tutorial years ago about writing a NN for doing character recognition. Was very cool.

    Afraid my maths etc aren’t really strong enough for things like tensorflow etc.

    Not to mention making the time to learn it all!

    Congrats on this fun achievement!
  • 9
    but can you exit Vim?
  • 20
    This dude is in hs and finished a neural network project in c. Thats passion right there my dude. Mad kudos to you bud, you are gonna do some amazing shit if you keep this up.
  • 7
    @AleCx04 I love you bro. Just with motivation from your comment I'm feeling like I could just get back to code and make one that's gonna recognise your profile pic among other devRanters and don't quit until it's finished.
    I feel like an extreme newb but I really appreciate your warm comment.. Thank you, I'm melting from all this, sorry XD
  • 5
    @spoiledgoods You mean unplugging PC from wall ? Yes, sir
  • 1
    @Brolls I'd love to check that out! Sounds awesome. And don't underestimate yourself. Maths SEEMS hard. But with things like Khan Academy, you can achieve basically anything you want. It's just attitude and time dedication (you don't have to rush). Good luck with everything anyway!
  • 7
    Did you just coded neural network in C? Man, you rock. Consider using Sublime Text though!
  • 1
    @uyouthe Thanks! It's pure C with just standard libs.
    Sublime always got my attention, but I never really got to using it / learning how to make the best from it. But I will definitely do so asap!
  • 3
    Kudos, keep it up!
  • 4
    Building a neural network with little or no IT education, even if basic is still a great achievement. Well done.
  • 2
    @Lahsen2016 I know FANN, but I wanna understand it in its entirety and made it from scratch. Thank you!
  • 2
    @shinobiultra aww shucks, much love to you too man! You got this. Just keep going and don't stop! Ill subscribe to see what other awesome stuff you come up with!
  • 4
    @Binary I'm just curious what IDE/text editor does @non-binary use...
  • 1
    Good job. 🍪
  • 4
    You're better than me.
    You did and understand it.
    I didn't, but I still want to.
  • 2
    Woah thats neat, grats dude. What exactly is it doing?
  • 2
    When I see the 3 layer nested for loop, someone give this poor kid a vectorization math library 😓
  • 2
    @shinobiultra ya just rip that mfkn cord out my dude. but for reals that's amazing, please have my babies so they can grow up to be geniuses
  • 3
    @shinobiultra Shameless request: Would love to see the source.
  • 2
    @CozyPlanes It's really bad, and mostly inconsistent. With my ""custom"" arrays it's extremely unreadable and bad. But I'm gonna write something I'm not ashamed for soon. https://github.com/shinobiultra/...
    @BindView It's learning to XOR. I give it two inputs (1/0) and it gives result (0-1). If it's wrong, it "learns" through something called backpropagation. I keep doing that until it's close enough.

    And OMG all you guys thanks for that support!!!!! I love you all!! Really
Add Comment