diff --git a/develop/api_doc/v2/fluid/layers.html b/develop/api_doc/v2/fluid/layers.html
index 40cc30fedc3199fee6a55906369d966c1a6dd1cc..54d3c11f384227d34275a35c79d64f3b5b0b9e86 100644
--- a/develop/api_doc/v2/fluid/layers.html
+++ b/develop/api_doc/v2/fluid/layers.html
@@ -1053,7 +1053,7 @@ a biases variable will be created and added to the output. Finally,
if activation is not None, it will be applied to the output as well.
This process can be formulated as follows:
-\[Out = Act({\sum_{i=0}^{N-1}W_iX_i + b})\]
+\[Out = Act({\sum_{i=0}^{N-1}X_iW_i + b})\]
In the above equation:
- \(N\): Number of the input.
diff --git a/develop/doc/api/v2/fluid/layers.html b/develop/doc/api/v2/fluid/layers.html
index 2b9d52e20cc1fd22dc267cc04ea3befb1e9baebf..40bff2f4b020743f5ba46319a951eaa45cadc39c 100644
--- a/develop/doc/api/v2/fluid/layers.html
+++ b/develop/doc/api/v2/fluid/layers.html
@@ -1103,7 +1103,7 @@ a biases variable will be created and added to the output. Finally,
if activation is not None, it will be applied to the output as well.
This process can be formulated as follows:
-\[Out = Act({\sum_{i=0}^{N-1}W_iX_i + b})\]
+\[Out = Act({\sum_{i=0}^{N-1}X_iW_i + b})\]
In the above equation:
- \(N\): Number of the input.
diff --git a/develop/doc_cn/api/v2/fluid/layers.html b/develop/doc_cn/api/v2/fluid/layers.html
index ef9edd6e3a8f75b7dd71671e3991a2d8452887cd..559fb299f2a7bc359908bd0904affcac125544c5 100644
--- a/develop/doc_cn/api/v2/fluid/layers.html
+++ b/develop/doc_cn/api/v2/fluid/layers.html
@@ -1122,7 +1122,7 @@ a biases variable will be created and added to the output. Finally,
if activation is not None, it will be applied to the output as well.
This process can be formulated as follows:
-\[Out = Act({\sum_{i=0}^{N-1}W_iX_i + b})\]
+\[Out = Act({\sum_{i=0}^{N-1}X_iW_i + b})\]
In the above equation:
- \(N\): Number of the input.