NLP Wiki

User Tools

Site Tools

Trace:
ml:nn_architectures

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
ml:nn_architectures [2024/04/30 08:29] – [Sequence Networks] jmflanigml:nn_architectures [2025/03/25 07:34] (current) – [Sequence Networks] jmflanig
Line 12: Line 12:
   * [[https://arxiv.org/pdf/1701.06538.pdf|Sparsely-Gated Mixture-of-Experts]].  Used to greatly scale-up the number of parameters with (sub-linear? check this) increase in computation. Uses many overlapping feedforward networks that are gated by another network. 1000x improvements in model capacity.   * [[https://arxiv.org/pdf/1701.06538.pdf|Sparsely-Gated Mixture-of-Experts]].  Used to greatly scale-up the number of parameters with (sub-linear? check this) increase in computation. Uses many overlapping feedforward networks that are gated by another network. 1000x improvements in model capacity.
   * [[https://arxiv.org/pdf/1902.05770.pdf|Dou et al 2019 - Dynamic Layer Aggregation for Neural Machine Translation with Routing-by-Agreement]]   * [[https://arxiv.org/pdf/1902.05770.pdf|Dou et al 2019 - Dynamic Layer Aggregation for Neural Machine Translation with Routing-by-Agreement]]
 +  * [[https://arxiv.org/pdf/2204.00595|Dao et al 2022 - Monarch: Expressive Structured Matrices for Efficient and Accurate Training]]
  
 ===== Connections ===== ===== Connections =====
Line 44: Line 45:
   * [[https://arxiv.org/pdf/2105.03824.pdf|FNet]] A faster, attention-free Transformer architecture based on Fourier transforms   * [[https://arxiv.org/pdf/2105.03824.pdf|FNet]] A faster, attention-free Transformer architecture based on Fourier transforms
   * [[https://arxiv.org/pdf/2305.10991.pdf|Anthe: Less is More! A slim architecture for optimal language translation]]   * [[https://arxiv.org/pdf/2305.10991.pdf|Anthe: Less is More! A slim architecture for optimal language translation]]
 +  * [[https://arxiv.org/pdf/2305.13048|RWKV (Receptance Weighted Key Value) Network]] Information is passed across positions using a positional weight decay which gates the information. Allows parallel training like the transformer, but more efficient inference like the RNN
   * [[https://arxiv.org/pdf/2307.08621.pdf|RetNet (Retentive Network)]]   * [[https://arxiv.org/pdf/2307.08621.pdf|RetNet (Retentive Network)]]
  
Line 72: Line 74:
   * [[https://arxiv.org/pdf/2102.11972.pdf|Narang et al 2021]] Compares activation functions in the Transformer   * [[https://arxiv.org/pdf/2102.11972.pdf|Narang et al 2021]] Compares activation functions in the Transformer
  
 +===== Matrices ===
 +Various representations of matrices, such as sparse, or low-dimensional ones.
 +  * Tensor networks
 +  * [[https://arxiv.org/pdf/2106.09685|LoRA]]
 +  * [[https://arxiv.org/pdf/2204.00595|Monarch Matrices]]
  
 ===== Set and Pooling Networks ===== ===== Set and Pooling Networks =====
ml/nn_architectures.1714465780.txt.gz · Last modified: 2024/04/30 08:29 by jmflanig
Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki