fixed too-long error essage in markdown

chapter02_supervised-learning/linear-regression-gluon.ipynb

@@ -247,9 +247,7 @@
     "If we try invoking your model by calling ``net(nd.array([[0,1]]))``, \n",
     "we'll confront the following hideous error message:\n",
     "\n",
-    "``RuntimeError: Parameter dense1_weight has not been initialized. \n",
-    "Note that you should initialize parameters and create Trainer \n",
-    "with Block.collect_params() instead of Block.params because the later does not include Parameters of nested child Blocks``.\n",
+    "```RuntimeError: Parameter dense1_weight has not been initialized...```\n",
     "\n",
     "That's because we haven't yet told ``gluon`` what the *initial values* for our parameters should be!\n",
     "We initialize parameters by calling the `.initialize()` method of a Parameterdict. \n",