@aethrvmn

I'm not really saying they do. I was more making fun of myself there.

As a kid I did #assembly - first without an assembler using paper and debug (enter 0000 for all jumps until you know their addresses, write down in notebook, go back and adjust.. save to .com)

Then C.

Swore anything higher level was lazy and wrong.

Then basically learned #Python in my 30's - it felt wrong, but #numpy, #theano, so..

Now #Rust - makes me nostalgic for old stubborn ways. And for C.

#rustlang

@aethrvmn

It's funny, but the thing that *really* irritated me about #Python when I first started learning was indentation.

I hated it. I wanted brackets like any "proper" language.

But I also wanted to use #Theano, so Python it was.

Now I'm in #Rust and... aaaarrrrrgggghh I hate brackets!!! They're so hard to read!

It's taking me time to re-adjust now that I'm back in a "proper" language.

@aethrvmn
That's what I'm doing.

I've used #Python for a lot of years (since #Theano was *the* deep learning library and you had to learn Python to play with it), but I'm still in shock that so few lines could be a full web service with nice rendering, does HTTPS now, all that good stuff.

A month of #Rust and building functions inch by inch and screen-full by screen-full just makes that feel impossible and possibly magic.

I miss Youtube before #Youtubers became a thing. All sorts of terrific lectures and presentations and so much good and worthwhile material - all just a search away.

And now there's people who's thing is being "content creators" and having "channel followers" and they really do say "like and subscribe".

Great lectures and presentations when I was learning #Python and #Theano in 2016, when learning #Pytorch a few years later. Now I'm learning #Rust, and #Youtube is full of so much garbage.

@lowd And no, I have no industry experience either. I'm a hobbyist basically. Currently I'm a recently turned ex-dishwasher now a part-time pizza-dough maker '-). But I first got into machine learning around 2015 when #Theano was still the leading platform and I'm pretty sure #Tensorflow didn't exist yet. It's been fun watching the field grow from where it was then, but also frustrating because marketing is the "killer-app" so far as the field has turned into an industry.
@alexjc I miss #Theano. Of course I really don't miss how hard it was to get Nvidia drivers, CUDA, etc. etc. up and running back then.
Revista de Estudios Bizantinos. Volumen 2020 nº8 

Estudios bizantinos is a digital and international open-access journal of Byzantine Studies. It has been created by the Sociedad Española de Bizantinística and it welcomes scientific papers with original and high-quality content on any aspect of the Byzantine civilisation.

https://www.openhub.net/p/keras# #Keras is a minimalist, highly modular #NeuralNetworks library, written in #Python and capable of running either on top of either #TensorFlow or #Theano
The Keras Open Source Project on Open Hub

Waiting on weights, waiting on weights, waiting on weights to train. Looks like a few more days, maybe a week, and I'll have satisfactory neural encoder/decoder for audio frames and can start playing with RNNs using it to start learning instruments, notes, & rhythm, along with other tasks to include speech recognition and speaker re-identification. #theano #lasagne #neuralnets #machinelearning #audio