Methods › Sequential › Recurrent Neural Networks › mRNN
Multiplicative RNN
mRNN
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A Multiplicative RNN (mRNN) is a type of recurrent neural network with multiplicative connections. In a standard RNN, the current input xₜ is first transformed via the visible-to-hidden weight matrix Wₕₓ and then contributes additively to the input for the current hidden state. An mRNN allows the current input (a character in the original example) to affect the hidden state dynamics by determining the entire hidden-to-hidden matrix (which defines the non-linear dynamics) in addition to providing an additive bias.
To achieve this goal, the authors modify the RNN so that its hidden-to-hidden weight matrix is a (learned) function of the current input xₜ:
hₜ = tanh(Wₕₓxₜ + Wₕₕ^((x_y))hₜ₋₁ + bₕ)
oₜ = Wₒₕhₜ + bₒ
This is the same as the equations for a standard RNN, except that Wₕₕ is replaced with W⁽ˣᵗ⁾ₕₕ. allowing each input (character) to specify a different hidden-to-hidden weight matrix.
Papers archive 2025-07-28
1 shown of 1, 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.
-
Data-driven Preference Learning Methods for Sorting Problems with Multiple Temporal Criteria 22 Sep 2023 · 0 repositories · arXiv:2309.12620
Tasks archive 2025-07-28
1 task the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Ensemble Learning | 1 |
Usage over time archive 2025-07-28
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
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