update some example readme

examples/DisturbLabel/README.md

@@ -23,4 +23,4 @@ The method didn't work for slightly harder problems such as SVHN:
 The SVHN experiements used the model & hyperparemeters as my original [svhn example](../svhn-digit-convnet.py).
 Experiements were all repeated 10 times to get the error bar.
 
-And I don't believe it will work for ImageNet either.
+And I don't believe it will work for ImageNet either. And that's a CVPR paper..

examples/ResNet/README.md

@@ -11,3 +11,5 @@ The validation error here is computed on test set.
 
 Download model:
 [Cifar10 ResNet-110 (n=18)](https://drive.google.com/open?id=0B9IPQTvr2BBkTXBlZmh1cmlnQ0k)
+
+Also see an implementation of [DenseNet](https://github.com/YixuanLi/densenet-tensorflow) from [Densely Connected Convolutional Networks](https://arxiv.org/abs/1608.06993).

examples/char-rnn/README.md

 
 ## Character-Level RNN Language Model
 
+To train, create some corpus in `input.txt`, and run `./char-rnn.py train`.
+Some corpus to play with: http://cs.stanford.edu/people/karpathy/char-rnn/
+
+To genearate text, see `./char-rnn.py sample --help` for the options.
+
+
 Generate linux kernel source code:
 ```c
 static int via_playback_set_interrupt(int action, void *data, int val)

examples/char-rnn/char-rnn.py

@@ -34,7 +34,6 @@ param.grad_clip = 5.
 param.vocab_size = None
 param.softmax_temprature = 1
 param.corpus = 'input.txt'
-# Get corpus to play with at: http://cs.stanford.edu/people/karpathy/char-rnn/
 
 class CharRNNData(DataFlow):
     def __init__(self, input_file, size):