I wonder if we can push-pop information by making LSTM look like this…
- It would be useful to have a stack type information storage device to handle cases where another language model is nested in the language model (e.g., program source code in a blog post).
This page is auto-translated from /nishio/LSTMをスタックに using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I’m very happy to spread my thought to non-Japanese readers.