Methods › General › Feedforward Networks › Boom Layer

Boom Layer

2 papers tagged archive 2025-07-28

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.

Source: Single Headed Attention RNN: Stop Thinking With Your HeadSee Code · Smerity/sha-rnn

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.

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.

TaskPapers
GPU1
Hyperparameter Optimization1
Language Modeling1
Language Modelling1

Usage over time archive 2025-07-28

Papers per year tagged with Boom Layer: 2019 to 2021, peak 1 1 0 2019: 1 paper 2019 2020: 0 papers 2020 2021: 1 paper 2021
Papers per year the archive tags with this method, by the paper's archive date (2 dated). Bars are counts, not a trend claim.

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

Feedforward Networks

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