Update Docs by revising --no_merge_train_val to --merge_train_val

Author: Kuan-Ting Chen

docs/tutorials/Parameter_Selection_for_Neural_Networks.rst

@@ -244,7 +244,7 @@ the log, extracts the performance metrics for each epoch, and identifies the opt
     print(best_epoch)
 
 In this case, the optimal epoch should be 42.
-We then specify ``--no_merge_train_val`` to include the validation set for training and 
+We then specify ``--merge_train_val`` to include the validation set for training and 
 specify the number of epochs by ``--epochs``. Note that options explicitly defined 
 override those in the configuration file. Because of no validation set, only the model
 at the last epoch is returned.
@@ -267,4 +267,4 @@ Similar with the last case, the test performance improves after re-training:
    * - 22.65
      - 57.06
      - 83.10
-     - 56.34
+     - 56.34