Merge pull request tensorflow#765 from dongjoon-hyun/fix_typos_in_tutorials. Closes tensorflow#765

Vijay Vasudevan · Vijay Vasudevan · commit 27c7dd72bede · 2016-01-13T16:05:09.000-08:00
diff --git a/tensorflow/g3doc/tutorials/mnist/tf/index.md b/tensorflow/g3doc/tutorials/mnist/tf/index.md
@@ -390,7 +390,7 @@ summary_writer = tf.train.SummaryWriter(FLAGS.train_dir,
 ```
 
 Lastly, the events file will be updated with new summary values every time the
-`summary_op` is run and the ouput passed to the writer's `add_summary()`
+`summary_op` is run and the output passed to the writer's `add_summary()`
 function.
 
 ```python
diff --git a/tensorflow/g3doc/tutorials/recurrent/index.md b/tensorflow/g3doc/tutorials/recurrent/index.md
@@ -10,7 +10,7 @@ for an introduction to recurrent neural networks and LSTMs in particular.
 
 In this tutorial we will show how to train a recurrent neural network on
 a challenging task of language modeling. The goal of the problem is to fit a
-probabilistic model which assigns probablities to sentences. It does so by
+probabilistic model which assigns probabilities to sentences. It does so by
 predicting next words in a text given a history of previous words. For this
 purpose we will use the Penn Tree Bank (PTB) dataset, which is a popular
 benchmark for measuring quality of these models, whilst being small and
@@ -80,7 +80,7 @@ of unrolled steps.
 This is easy to implement by feeding inputs of length `num_steps` at a time and
 doing backward pass after each iteration.
 
-A simplifed version of the code for the graph creation for truncated
+A simplified version of the code for the graph creation for truncated
 backpropagation:
 
 ```python
@@ -129,7 +129,7 @@ word_embeddings = tf.nn.embedding_lookup(embedding_matrix, word_ids)
 The embedding matrix will be initialized randomly and the model will learn to
 differentiate the meaning of words just by looking at the data.
 
-### Loss Fuction
+### Loss Function
 
 We want to minimize the average negative log probability of the target words:
 
diff --git a/tensorflow/g3doc/tutorials/seq2seq/index.md b/tensorflow/g3doc/tutorials/seq2seq/index.md
@@ -50,7 +50,7 @@ This basic architecture is depicted below.
 Each box in the picture above represents a cell of the RNN, most commonly
 a GRU cell or an LSTM cell (see the [RNN Tutorial](../../tutorials/recurrent/index.md)
 for an explanation of those). Encoder and decoder can share weights or,
-as is more common, use a different set of parameters. Mutli-layer cells
+as is more common, use a different set of parameters. Multi-layer cells
 have been successfully used in sequence-to-sequence models too, e.g. for
 translation [Sutskever et al., 2014](http://arxiv.org/abs/1409.3215).
 
@@ -203,7 +203,7 @@ sentence with a special PAD symbol. Then we'd need only one seq2seq model,
 for the padded lengths. But on shorter sentence our model would be inefficient,
 encoding and decoding many PAD symbols that are useless.
 
-As a compromise between contructing a graph for every pair of lengths and
+As a compromise between constructing a graph for every pair of lengths and
 padding to a single length, we use a number of *buckets* and pad each sentence
 to the length of the bucket above it. In `translate.py` we use the following
 default buckets.
