Backward propagation -> Backpropagation

kakaobrain · Jun 20, 2019 · 7de9a54 · 7de9a54
1 parent 15476df
commit 7de9a54
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/README.ko.md b/README.ko.md
@@ -42,7 +42,7 @@ GPipe는 Pipeline Parallelism과 Checkpointing, 두 가지 방법으로 가능
 <dt>Checkpointing</dt>
 <dd>각 파티션엔 체크포인트를 만들어 메모리 가용량을 극대화한다. 순전파(forward
     propagation) 때 파티션 경계의 입출력만 기억하고 내부의 히든레이어는
-    휘발시킨다. 휘발된 히든레이어는 역전파(backward propagation) 때 다시
+    휘발시킨다. 휘발된 히든레이어는 역전파(backpropagation) 때 다시
     계산된다.</dd>
 </dl>
 

diff --git a/README.md b/README.md
@@ -47,7 +47,7 @@ terminology in PyTorch community.
 <dd>Checkpointing is applied to each partition to minimize the overall memory
     consumption by a model. During forward propagation, only the tensors at the
     boundaries between partitions are remembered. All other intermediate
-    tensors are volatilized, and recomputed during backward propagation when
+    tensors are volatilized, and recomputed during backpropagation when
     necessary.</dd>
 </dl>