{"url":"/method/boom-layer","slug":"boom-layer","name":"Boom Layer","full_name":"Boom Layer","full_name_withheld":false,"description_markdown":"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 $v \\in \\mathbb{R}^{H}$ and uses a matrix\r\nmultiplication with a GeLU activation to produce a vector $u \\in \\mathbb{R}^{N\\times{H}}$. We then break $u$ into $N$ vectors and sum those together, producing $w \\in \\mathbb{R}^{H}$. This minimizes computation and removes an entire matrix of parameters compared to traditional down-projection layers.\r\n\r\nThe Figure to the right shows the Boom Layer used in the context of [SHA-RNN](https://paperswithcode.com/method/sha-rnn) from the original paper.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/1911.11423v2","title":"Single Headed Attention RNN: Stop Thinking With Your Head","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/Smerity/sha-rnn/blob/218d748022dbcf32d50bbbb4d151a9b6de3f8bba/model.py#L341","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Feedforward Networks","url":"/methods/category/feedforward-networks","pwc_aliases":[]}],"n_papers_tagged":2,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"title":"SHAQ: Single Headed Attention with Quasi-Recurrence","date":"2021-08-18","arxiv_id":"2108.08207","n_code_links":0,"syntology":null},{"paper":"/paper/single-headed-attention-rnn-stop-thinking","title":"Single Headed Attention RNN: Stop Thinking With Your Head","date":"2019-11-26","arxiv_id":"1911.11423","n_code_links":5,"syntology":null}],"papers_shown":2,"tasks":[{"task":null,"name":"GPU","papers":1},{"task":"/task/hyperparameter-optimization","name":"Hyperparameter Optimization","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1}],"tasks_shown":4,"n_tasks":4,"usage_by_year":[{"year":"2019","papers":1},{"year":"2021","papers":1}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/boom-layer"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}