Zobrazeno 1 - 10
of 85
pro vyhledávání: '"Smith, A. T. H."'
Efficient state space models (SSMs), such as linear recurrent neural networks and linear attention variants, offer computational advantages over Transformers but struggle with tasks requiring long-range in-context retrieval-like text copying, associa
Externí odkaz:
http://arxiv.org/abs/2411.01030
Conventional nonlinear RNNs are not naturally parallelizable across the sequence length, unlike transformers and linear RNNs. Lim et. al. (2024) therefore tackle parallelized evaluation of nonlinear RNNs, posing it as a fixed point problem solved wit
Externí odkaz:
http://arxiv.org/abs/2407.19115
State space models (SSMs) have shown remarkable empirical performance on many long sequence modeling tasks, but a theoretical understanding of these models is still lacking. In this work, we study the learning dynamics of linear SSMs to understand ho
Externí odkaz:
http://arxiv.org/abs/2407.07279
Autor:
Parnichkun, Rom N., Massaroli, Stefano, Moro, Alessandro, Smith, Jimmy T. H., Hasani, Ramin, Lechner, Mathias, An, Qi, Ré, Christopher, Asama, Hajime, Ermon, Stefano, Suzuki, Taiji, Yamashita, Atsushi, Poli, Michael
We approach designing a state-space model for deep learning applications through its dual representation, the transfer function, and uncover a highly efficient sequence parallel inference algorithm that is state-free: unlike other proposed algorithms
Externí odkaz:
http://arxiv.org/abs/2405.06147
Effectively modeling long spatiotemporal sequences is challenging due to the need to model complex spatial correlations and long-range temporal dependencies simultaneously. ConvLSTMs attempt to address this by updating tensor-valued states with recur
Externí odkaz:
http://arxiv.org/abs/2310.19694
Models using structured state space sequence (S4) layers have achieved state-of-the-art performance on long-range sequence modeling tasks. An S4 layer combines linear state space models (SSMs), the HiPPO framework, and deep learning to achieve high p
Externí odkaz:
http://arxiv.org/abs/2208.04933
Recurrent neural networks (RNNs) are powerful models for processing time-series data, but it remains challenging to understand how they function. Improving this understanding is of substantial interest to both the machine learning and neuroscience co
Externí odkaz:
http://arxiv.org/abs/2111.01256
Autor:
Smith, A. T. H.
Publikováno v:
The Cambridge Law Journal, 2006 Jul 01. 65(2), 251-254.
Externí odkaz:
https://www.jstor.org/stable/4509191
Autor:
Smith, A. T. H.
Publikováno v:
The Cambridge Law Journal, 2004 Mar 01. 63(1), 4-7.
Externí odkaz:
https://www.jstor.org/stable/4509058
Autor:
Smith, A. T. H.
Publikováno v:
The Cambridge Law Journal, 2003 Jul 01. 62(2), 241-244.
Externí odkaz:
https://www.jstor.org/stable/4508985