jrzaurin / pytorch-widedeep

A flexible package for multimodal-deep-learning to combine tabular data with text and images using Wide and Deep models in Pytorch

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Editorial comment

osorensen opened this issue · comments

This equation is too wide for a single line.

image

I suggest to write it more compact using summation, as

$$pred = \sigma(W_{wide}^{T}[x,\phi(x)] + \sum_{i \in \mathcal{I}} W_{i}^{T}a_{i}^{l_f} + b)$$

where you then need to add a description in the text below that \mathcal{I} = \{deeptabular, deeptext, deepimage \}.

The LaTeX for this is

pred = \sigma(W_{wide}^{T}[x,\phi(x)] + \sum_{i \in \mathcal{I}} W_{i}^{T}a_{i}^{l_f} + b)

openjournals/joss-reviews#5027

thank you for the comment, the issue is resolved in the latest version of the paper. Also, thank you for already writing down the new formula :) !!!
image