Comment by OkayPhysicist
1 year ago
The most popular RNNs (the ones that were successful enough for Google translate and the like) actually had this behavior baked in to the architecture, called "LSTMs", "Long-Short Term Memory"
1 year ago
The most popular RNNs (the ones that were successful enough for Google translate and the like) actually had this behavior baked in to the architecture, called "LSTMs", "Long-Short Term Memory"
No comments yet
Contribute on Hacker News ↗