Methods › General › Feedforward Networks › Boom Layer
Boom Layer
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A Boom Layer is a type of feedforward layer that is closely related to the feedforward layers used in Transformers. The layer takes a vector of the form v ∈ℝᴴ and uses a matrix multiplication with a GeLU activation to produce a vector u ∈ℝ^(N×H). We then break u into N vectors and sum those together, producing w ∈ℝᴴ. This minimizes computation and removes an entire matrix of parameters compared to traditional down-projection layers.
The Figure to the right shows the Boom Layer used in the context of SHA-RNN from the original paper.
Papers archive 2025-07-28
2 shown of 2, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
SHAQ: Single Headed Attention with Quasi-Recurrence 18 Aug 2021 · 0 repositories · arXiv:2108.08207
-
Single Headed Attention RNN: Stop Thinking With Your Head 26 Nov 2019 · 5 repositories · arXiv:1911.11423
Tasks archive 2025-07-28
4 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| GPU | 1 |
| Hyperparameter Optimization | 1 |
| Language Modeling | 1 |
| Language Modelling | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections