Methods › General › Feedforward Networks › Dense Connections

Dense Connections

29,230 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output by a weight. This means there are nᵢₙₚᵤₜₛ*nₒᵤₜₚᵤₜₛ parameters, which can lead to a lot of parameters for a sizeable network.

hₗ = g(Wᵀhₗ₋₁)

where g is an activation function.

Image Source: Deep Learning by Goodfellow, Bengio and Courville

Papers archive 2025-07-28

30 shown of 29,230, 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

20 shown of 2,754 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
Language Modelling3,021
Language Modeling2,367
Retrieval1,867
Question Answering1,503
Decoder1,485
RAG1,355
Sentence1,339
Retrieval-augmented Generation1,176
Image Classification1,107
Semantic Segmentation1,103
Translation1,065
Transfer Learning965
Machine Translation927
image-classification866
Object Detection859
Large Language Model848
Classification802
Reinforcement Learning (RL)778
Representation Learning774
Segmentation773

Usage over time archive 2025-07-28

Papers per year tagged with Dense Connections: 2012 to 2025, peak 7,495 7,495 0 2012: 1 paper 2012 2013: 4 papers 2013 2014: 11 papers 2014 2015: 50 papers 2015 2016: 89 papers 2016 2017: 199 papers 2017 2018: 459 papers 2018 2019: 1529 papers 2019 2020: 2803 papers 2020 2021: 3828 papers 2021 2022: 3886 papers 2022 2023: 5875 papers 2023 2024: 7495 papers 2024 2025: 3001 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (29,230 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