top | item 19506608 (no title) slashcom | 7 years ago And replaced by residual connections in transformers, which are absolutely dominating LSTMs now. discuss order hn newest stochastic_monk|7 years ago Transformer-XL uses recurrence, and most NLP SOTA is still with LSTMs. I’m not sure I’d expect attention mechanisms to fully replace recurrence.
stochastic_monk|7 years ago Transformer-XL uses recurrence, and most NLP SOTA is still with LSTMs. I’m not sure I’d expect attention mechanisms to fully replace recurrence.
stochastic_monk|7 years ago