My Neural Network can recognise handwritten digits!!!

It's my second try at NN so it's faaaar from perfect (or maybe even good), but hey, it's something and only with High schools, I'm pretty satisfied with the results. If you've not seen my previous post, I'm just trying to learn NNs in C and am doing just really basic things.
Still I'm proud of my progress!

Now I'm looking forward learning some library (OpenNN + OpenCV seems cool) and trying more advanced stuff, wish me luck 😆

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

Today, one of my coworkers had to translate a bunch of pages to French ...
He did his job, committed, pushed, and asked someone to validate his branch in order to merge.
Tests didn't take long, the login screen was broken, because there was an there was an <input type="mot de passe"> ...

anyone i can talk to about artificial intelligence and nns?

on an somewhat note, we should make a list of ranters willing to help newbies when theyre stuck

After a year in cloud I decided to start a master's degree in AI and Robotics. Happy as fuck.

Yet I got really disappointed by ML and NNs. It's like I got told the magician's trick and now the magic is ruined.

Still interesting though.

What I have learned from neutral networks for my life.

It's already a year that I'm familiar with NNs. I did not write anything serious and did not learn it that deep. But, actually, the basic knowledge gave me an interesting view to my life. I just want to share one fact with you.

There is a learning speed in NNs, which specifies how fast does the network learn. If it is too high, any new information will be accepted very easily but will wipe the past of the network's knowledge and if it is too low, the network will hardly accept new info but remember everything. When people born, they learn everything very fast and by the age they become more hard-learners Here, I've learned that you should not live in the past, and not for the current day. You just have to keep the balance.

I was too lazy to download videos one by one so I created a script to download playlists and rename the downloaded files !

since my only team mate of my chess engine left, i gotta ask again:

anybody in to help coding a chess engine that is based on NN tech?

Is it just me or feeling the imposter syndrome, and blogging about it is super trendy at the moment ?

Hoy to all!

I need advice for NNs.

I wanna make a chess engine that uses an NN. (see collabs)

I want the NN to output a probability for each move.

However, i dont know what data to train the NN with.

If i train it with the moves from an engine, it simulates an engine and that sucks.

If i train it from games, i only see one move, and thus, cant train the other moves.

My thougt is, that maybe, i let the NN play an entire game and if it loses, it adjusts itself somehow. But how?

If you wanna contribute, email me :wittmaxi@outlook.de