Fix Typos

cognitive_mapping_and_planning/README.md

@@ -106,7 +106,7 @@ citing the following paper:
 
 ### Train Your Own Models
 All models were trained asynchronously with 16 workers each worker using data
-from a single floor. The default hyper-parameters coorespond to this setting.
+from a single floor. The default hyper-parameters correspond to this setting.
 See [distributed training with
 Tensorflow](https://www.tensorflow.org/deploy/distributed) for setting up
 distributed training. Training with a single worker is possible with the current

inception/README.md

@@ -260,7 +260,7 @@ Note that in this example each replica has a single tower that uses one GPU.
 The command-line flags `worker_hosts` and `ps_hosts` specify available servers.
 The same binary will be used for both the `worker` jobs and the `ps` jobs.
 Command line flag `job_name` will be used to specify what role a task will be
-playing and `task_id` will be used to idenify which one of the jobs it is
+playing and `task_id` will be used to identify which one of the jobs it is
 running. Several things to note here:
 
 *   The numbers of `ps` and `worker` tasks are inferred from the lists of hosts

skip_thoughts/README.md

@@ -285,7 +285,7 @@ bazel-bin/skip_thoughts/vocabulary_expansion \
 
 The model can be evaluated using the benchmark tasks described in the
 [Skip-Thought Vectors](https://papers.nips.cc/paper/5950-skip-thought-vectors.pdf)
-paper. The following tasks are suported (refer to the paper for full details):
+paper. The following tasks are supported (refer to the paper for full details):
 
  * **SICK** semantic relatedness task.
  * **MSRP** (Microsoft Research Paraphrase Corpus) paraphrase detection task.