提交 5d43badc authored 作者: --global's avatar --global

Fix typo

上级 f7302dfd
...@@ -510,7 +510,7 @@ This one is simple but still worth pointing out. Theano is able to ...@@ -510,7 +510,7 @@ This one is simple but still worth pointing out. Theano is able to
automatically recognize and optimize many computation patterns. However, there automatically recognize and optimize many computation patterns. However, there
are patterns that Theano doesn't optimize because doing so would change the are patterns that Theano doesn't optimize because doing so would change the
user interface (such as merging shared variables together into a single one, user interface (such as merging shared variables together into a single one,
for instance). Additionnaly, Theano doesn't catch every case that it could for instance). Additionaly, Theano doesn't catch every case that it could
optimize and so it remains useful for performance that the user defines an optimize and so it remains useful for performance that the user defines an
efficient graph in the first place. This is also the case, and sometimes even efficient graph in the first place. This is also the case, and sometimes even
more so, for the graph inside of Scan. This is because it will be executed more so, for the graph inside of Scan. This is because it will be executed
...@@ -525,8 +525,8 @@ multiplications between matrix :math:`x_t` and each of the shared matrices ...@@ -525,8 +525,8 @@ multiplications between matrix :math:`x_t` and each of the shared matrices
performs a single larger matrix multiplication between :math:`W` and performs a single larger matrix multiplication between :math:`W` and
:math:`x_t`. The resulting matrix is then sliced to obtain the results of that :math:`x_t`. The resulting matrix is then sliced to obtain the results of that
the small individual matrix multiplications would have produced. This the small individual matrix multiplications would have produced. This
optimization replaces many small and inefficient matrix multiplications but a optimization replaces several small and inefficient matrix multiplications by
single larger one and thus improves performance at the cost of a potentially a single larger one and thus improves performance at the cost of a potentially
higher memory usage. higher memory usage.
......
Markdown 格式
0%
您添加了 0 到此讨论。请谨慎行事。
请先完成此评论的编辑!
注册 或者 后发表评论