From 7cf22ac42e4e702b7e61a4f1eb30018a237fb9bc Mon Sep 17 00:00:00 2001 From: DavidLeon Date: Tue, 6 Nov 2018 16:36:12 +0800 Subject: [PATCH] improve documentation --- docs/dandelion_module.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/dandelion_module.md b/docs/dandelion_module.md index f59603f..001b638 100644 --- a/docs/dandelion_module.md +++ b/docs/dandelion_module.md @@ -293,7 +293,7 @@ All the parameters have the same meanings with `Conv2D` module. In fact, the tra _______________________________________________________________________ ## Dense -Fully connected network, also known as affine transform. Apply affine transform `Wx+b` to the last dimension of input. +Fully connected network, also known as affine transform. Apply affine transform $Wx+b$ to the last dimension of input. The input of `Dense` can have any dimensions, and note that we do not apply any activation to its output by default ```python class Dense(input_dims, output_dim, W=init.GlorotUniform(), b=init.Constant(0.), name=None)