How to represent the number of neurons in an LSTM for architecture schematic?

I'm trying to visualise a neural network schematic and found a great tool for building schematics here http://alexlenail.me/NN-SVG/index.html. I've edited the SVG file to change one of the dense layers into a LSTM layer, and the input to time series instead of singular neurons.

At the bottom of the image there is some set notation detailing how many neurons is in each layer. I'm not too familiar with set notation. I'm not quite sure how to represent the LSTM layers the number of neurons in accordance with the set notation given?

Its a singular LSTM layer with hidden_size=8 and the input/output size is obviously just the previous/next layers (5 and 8).

Also, the same question applies for the initial time series inputs; how to represent 5 time series of (say 100 points long) in set notation?

Any additional advice on how it might be better to represent the architecture would also be appreciated! Thanks!

Topic lstm rnn neural-network visualization

Category Data Science


Within the recurrent cell, you can add the hidden units- often, we se this notated as:

Unit 1
  ...  
Unit n

Where n is the dimensionality of the recurrent representation.

About

Geeks Mental is a community that publishes articles and tutorials about Web, Android, Data Science, new techniques and Linux security.