Merge pull request #1586 from Molkree:patch-1

PiperOrigin-RevId: 314185237

Author: copybara-github

site/en/guide/keras/custom_layers_and_models.ipynb

@@ -821,7 +821,7 @@
         "\n",
         "Here's what you've learned so far:\n",
         "\n",
-        "- A `Layer` encapsulate a state (created in `__init__` or `build`) and some computation (in `call`).\n",
+        "- A `Layer` encapsulates a state (created in `__init__` or `build`) and some computation (in `call`).\n",
         "- Layers can be recursively nested to create new, bigger computation blocks.\n",
         "- Layers can create and track losses (typically regularization losses).\n",
         "- The outer container, the thing you want to train, is a `Model`. A `Model` is just like a `Layer`, but with added training and serialization utilities.\n",