Fix a typo in GRU page (d2l-ai#2269)

* Fix a typo in GRU page * Fixed a typo in lstm.md
naviat · Aug 26, 2022 · e8ff88d · e8ff88d
1 parent 3b40fce
commit e8ff88d
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/chapter_recurrent-modern/gru.md b/chapter_recurrent-modern/gru.md
@@ -301,7 +301,7 @@ They can also skip subsequences by turning on the update gate.
 ## Exercises
 
 1. Assume that we only want to use the input at time step $t'$ to predict the output at time step $t > t'$. What are the best values for the reset and update gates for each time step?
-1. Adjust the hyperparameters and analyze the their influence on running time, perplexity, and the output sequence.
+1. Adjust the hyperparameters and analyze their influence on running time, perplexity, and the output sequence.
 1. Compare runtime, perplexity, and the output strings for `rnn.RNN` and `rnn.GRU` implementations with each other.
 1. What happens if you implement only parts of a GRU, e.g., with only a reset gate or only an update gate?
 

diff --git a/chapter_recurrent-modern/lstm.md b/chapter_recurrent-modern/lstm.md
@@ -424,7 +424,7 @@ LSTMs can alleviate vanishing and exploding gradients.
 
 ## Exercises
 
-1. Adjust the hyperparameters and analyze the their influence on running time, perplexity, and the output sequence.
+1. Adjust the hyperparameters and analyze their influence on running time, perplexity, and the output sequence.
 1. How would you need to change the model to generate proper words as opposed to sequences of characters?
 1. Compare the computational cost for GRUs, LSTMs, and regular RNNs for a given hidden dimension. Pay special attention to the training and inference cost.
 1. Since the candidate memory cell ensures that the value range is between $-1$ and $1$ by  using the $\tanh$ function, why does the hidden state need to use the $\tanh$ function again to ensure that the output value range is between $-1$ and $1$?