Methods › General › Activation Functions › Tanh Activation

Tanh Activation

6,333 papers tagged archive 2025-07-28

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

Tanh Activation is an activation function used for neural networks:

f(x) = (eˣ - e⁻ˣ)/(eˣ + e⁻ˣ)

Historically, the tanh function became preferred over the sigmoid function as it gave better performance for multi-layer neural networks. But it did not solve the vanishing gradient problem that sigmoids suffered, which was tackled more effectively with the introduction of ReLU activations.

Image Source: Junxi Feng

See Code · pytorch/pytorch

In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.

Near matches the lookup lists, each a different name: Activation Flow; Activation Prompt; Activation Oracles; Dynamic Tanh (DyT); Dynamic Tanh (DyT); Activation Oracles; activation steering; Activation Steering.

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.

Papers archive 2025-07-28

archive papers tagged: 6,333 · with a code link: 2,134 · where Syntology ran a sample: 386 (323 with a run with no instrument failure, 63 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (386 of 6,333 tagged: 323 with a run with no instrument failure, 63 where every run was a failure of Syntology's instrument)

Page 1 of 64: papers 1 to 100 of 6,333, 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

20 shown of 1,433 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
Sentence436
Time Series406
Language Modelling405
Decoder358
Time Series Analysis340
Language Modeling332
General Classification313
Translation312
Neural Architecture Search277
Prediction276
Sentiment Analysis258
Deep Learning235
Machine Translation231
Classification216
Word Embeddings209
Speech Recognition208
speech-recognition196
Transfer Learning186
Data Augmentation162
Reinforcement Learning155

Usage over time archive 2025-07-28

Papers per year tagged with Tanh Activation: 2014 to 2025, peak 1,098 1,098 0 2014: 14 papers 2014 2015: 57 papers 2015 2016: 179 papers 2016 2017: 332 papers 2017 2018: 659 papers 2018 2019: 1009 papers 2019 2020: 1098 papers 2020 2021: 898 papers 2021 2022: 643 papers 2022 2023: 609 papers 2023 2024: 583 papers 2024 2025: 252 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (6,333 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

Activation Functions

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