1603.08983
arxiv.org · 7,521 words · saved by 1 readers
N/A
Adaptive Computation Time for Recurrent Neural Networks arXiv:1603.08983v6 [cs.NE] 21 Feb 2017 Alex Graves Google DeepMind gravesa@google.com Abstract This paper…
saved by
related reading
- 2408.14690arxiv.org
- The Unreasonable Effectiveness of Recurrent Neural Networkskarpathy.github.io
- transformer_attention.pdfarxiv.org
- The Annotated Transformernlp.seas.harvard.edu
- 1706.03762arxiv.org
- [1701.06538] Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layerarxiv.org
- [2606.06479] Pretraining Recurrent Networks without Recurrencearxiv.org
- [2111.00396] Efficiently Modeling Long Sequences with Structured State Spacesarxiv.org
- 1301.3781arxiv.org
- [2501.00663] Titans: Learning to Memorize at Test Timearxiv.org
- Attention and Augmented Recurrent Neural Networksdistill.pub
- [2111.00396] Efficiently Modeling Long Sequences with Structured State Spacesarxiv.org