Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Show HN: I Parallelized RNN Training from O(T) to O(log T) Using CUDA. Parent comment
https://colah.github.io/posts/2015-08-Understanding-LSTMs/
Another great one (just on RNNs) is:
http://karpathy.github.io/2015/05/21/rnn-effectiveness/
https://colah.github.io/posts/2015-08-Understanding-LSTMs/
Another great one (just on RNNs) is:
http://karpathy.github.io/2015/05/21/rnn-effectiveness/