1 vote

Can an RNN predict a sinus curve with no input?

Consider that RNNs have an internal state, $h$, apart from the input sequence (and in particular, LSTMs have two of them), that got updated at each timestep of the input sequence during back-...
Luca Anzalone's user avatar
1 vote

Can an RNN predict a sinus curve with no input?

The universal approximation theorem states that, theoretically, any function (trivially including sine waves) can be approximated using a neural network of large enough size. Neural networks include ...
Robin van Hoorn's user avatar
1 vote

What is the number of neurons required to approximate a polynomial of degree n?

Not sure this is answering your question but, one way to get a general idea of the number of neurons needed is to consider the number of turning points in the polynomial. Each turning point in a ...
hH1sG0n3's user avatar
  • 201

Only top scored, non community-wiki answers of a minimum length are eligible