0
$\begingroup$

I am new to AI.

I have a series of numbers ranging from x to y and I have a lot of data to train with

What I am trying to do is, let's say from 0 to 1, I train it with data calculated over time and predict what may happen next, training it with my data and then feeding it the last few days and continue the pattern.

I have been thinking about using char-rnn, but from what i understand the data exported is arbitrary and not a continuation of a series. I oftentimes see videos on youtube "AI continues this song" so I'm wondering which I can use and where I can get started to do this myself.

Thank you and have a nice day ☺

$\endgroup$
0
$\begingroup$

I don't actually understand your question, but if your data is completely arbitrary, there is nothing to predict, it have no patterns to recognize or something like that.

But if you say that you are working with time-series data and it have some patterns, then you could start by trying to implement just the forward propagation of a simple RNN. I am really new as well at AI and the first RNN I code was a Elman RNN, and they were very simple equations to implement. I recommend you trying that, and then implement the backpropagation to that RNN.

Something that really helped me starting was searching simple github scrips for RNNs (around 100 lines of code) so that you can see their architecture.

About the example you give, the one about songs, they are actually really predictable, because you have the rime, rithm and tempo, and also they use to repeat the same secuence of notes every stanza.

Hope it helps :)

$\endgroup$

Not the answer you're looking for? Browse other questions tagged or ask your own question.