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

In Syntology harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='1702.05870'). Repositories: 1 listed of 1 in the graph, strongest link: mentioned on GitHub. The lookup matched a paper by its title, arXiv:1702.05870, not a method entry. This answer is about arXiv:1702.05870, the paper the archive credits with this method.

Origin paper of this answer, arXiv:1702.05870 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).

Papers archive 2025-07-28

archive papers tagged: 2 · with a code link: 2 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (1 of 2 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 2 of 2, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

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