Methods › General › Normalization › Cosine Normalization

Cosine Normalization

2 papers tagged archive 2025-07-28

Introduced by Chunjie Luo et al. in Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networks

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

Multi-layer neural networks traditionally use dot products between the output vector of previous layer and the incoming weight vector as the input to activation function. The result of dot product is unbounded. To bound dot product and decrease the variance, Cosine Normalization uses cosine similarity or centered cosine similarity (Pearson Correlation Coefficient) instead of dot products in neural networks.

Using cosine normalization, the output of a hidden unit is computed by:

o = f(netₙₒᵣₘ)= f(cosθ) = f((w⃗ ·x⃗)/(|w⃗| |x⃗|))

where netₙₒᵣₘ is the normalized pre-activation, w⃗ is the incoming weight vector and x⃗ is the input vector, (·) indicates dot product, f is nonlinear activation function. Cosine normalization bounds the pre-activation between -1 and 1.

PaperSourceSee Code · iwyoo/tf_conv_cosnorm

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

3 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
Class Incremental Learning1
Incremental Learning1
class-incremental learning1

Usage over time archive 2025-07-28

Papers per year tagged with Cosine Normalization: 2017 to 2020, peak 1 1 0 2017: 1 paper 2017 2018: 0 papers 2018 2019: 0 papers 2019 2020: 1 paper 2020
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

Normalization

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