diff --git a/develop/doc/api/v2/config/optimizer.html b/develop/doc/api/v2/config/optimizer.html index 5233b7ae2ad167f50bf2ef7725d8de65910e01c5..6e90175c955f11bf483a92e54ae3afea0f249ff8 100644 --- a/develop/doc/api/v2/config/optimizer.html +++ b/develop/doc/api/v2/config/optimizer.html @@ -205,7 +205,7 @@

Momentum Optimizer.

When sparse=False, the momentum update formula is as follows:

-\[\begin{split}v_{t} &= k * v_{t-1} - \gamma_t / (g_{t} + \lambda w_{t-1}) \\ +\[\begin{split}v_{t} &= k * v_{t-1} - \gamma_t (g_{t} + \lambda w_{t-1}) \\ w_{t} &= w_{t-1} + v_{t} \\\end{split}\]

where, \(k\) is momentum, \(\lambda\) is decay rate, \(\gamma_t\) is learning rate at the t’th iteration. diff --git a/develop/doc_cn/api/v2/config/optimizer.html b/develop/doc_cn/api/v2/config/optimizer.html index 62b5f70a59e78a446738ef9022722db7377b81cd..26a55e0b9fc1654f013d098da1f7adb2569e57df 100644 --- a/develop/doc_cn/api/v2/config/optimizer.html +++ b/develop/doc_cn/api/v2/config/optimizer.html @@ -219,7 +219,7 @@

Momentum Optimizer.

When sparse=False, the momentum update formula is as follows:

-\[\begin{split}v_{t} &= k * v_{t-1} - \gamma_t / (g_{t} + \lambda w_{t-1}) \\ +\[\begin{split}v_{t} &= k * v_{t-1} - \gamma_t (g_{t} + \lambda w_{t-1}) \\ w_{t} &= w_{t-1} + v_{t} \\\end{split}\]

where, \(k\) is momentum, \(\lambda\) is decay rate, \(\gamma_t\) is learning rate at the t’th iteration.