What exactly is timestep in an LSTM Model?

问题

I am a newbie to LSTM and RNN as a whole, I've been racking my brain to understand what exactly is a timestep. I would really appreciate an intuitive explanation to this

回答1:

Let's start with a great image from Chris Olah's blog (a highly recommended read btw):

In a recurrent neural network you have multiple repetitions of the same cell. The way inference goes is - you take some input (x₀), pass it through the cell to get some output₁(depicted with black arrow to the right on the picture), then pass output₁ as input(possibly adding some more input components - x₁ on the image) to the same cell, producing new output output₂, pass that again as input to the same cell(again with possibly additional input component x₂), producing output₃ and so on.

A time step is a single occurrence of the cell - e.g. on the first time step you produce output₁, h₀, on the second time step you produce output₂ and so on.

来源：https://stackoverflow.com/questions/54235845/what-exactly-is-timestep-in-an-lstm-model