未验证 提交 aa756a3d 编写于 作者: R ranqiu92 提交者: GitHub

Merge pull request #6940 from ranqiu92/doc

fix doc
...@@ -6629,7 +6629,7 @@ def row_conv_layer(input, ...@@ -6629,7 +6629,7 @@ def row_conv_layer(input,
.. math:: .. math::
r_{t,r} = \sum_{j=1}^{k + 1} {w_{i,j}h_{t+j-1, i}} r_{t,r} = \sum_{j=1}^{k + 1} {w_{i,j}h_{t+j-1, i}}
\quad \text{for} \quad (1 \leq i \leq d) \quad \\text{for} \quad (1 \leq i \leq d)
Note: Note:
The `context_len` is `k + 1`. That is to say, the lookahead step The `context_len` is `k + 1`. That is to say, the lookahead step
...@@ -6778,7 +6778,7 @@ def gated_unit_layer(input, ...@@ -6778,7 +6778,7 @@ def gated_unit_layer(input,
The gated unit layer implements a simple gating mechanism over the input. The gated unit layer implements a simple gating mechanism over the input.
The input :math:`X` is first projected into a new space :math:`X'`, and The input :math:`X` is first projected into a new space :math:`X'`, and
it is also used to produce a gate weight :math:`\sigma`. Element-wise it is also used to produce a gate weight :math:`\sigma`. Element-wise
product between :match:`X'` and :math:`\sigma` is finally returned. product between :math:`X'` and :math:`\sigma` is finally returned.
Reference: Reference:
`Language Modeling with Gated Convolutional Networks `Language Modeling with Gated Convolutional Networks
...@@ -7474,7 +7474,7 @@ def factorization_machine(input, ...@@ -7474,7 +7474,7 @@ def factorization_machine(input,
Factorization Machine with the formula: Factorization Machine with the formula:
.. math:: .. math::
y = \sum_{i=1}^{n-1}\sum_{j=i+1}^n\langle v_i, v_j \rangle x_i x_j y = \sum_{i=1}^{n-1}\sum_{j=i+1}^n\langle v_i, v_j \\rangle x_i x_j
Note: Note:
X is the input vector with size n. V is the factor matrix. Each row of V X is the input vector with size n. V is the factor matrix. Each row of V
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册