rnn-design-space-two-dimensional

IN derived (depth 1)

Created 2026-06-21T13:38:09+00:00 · Reviewed 2026-06-21T15:37:01+00:00

RNN design involves two orthogonal dimensions: cell architecture (vanilla RNN, LSTM, GRU) determines how hidden state is updated, while configuration (standard, stacked, bidirectional, encoder-decoder) determines data flow topology — the canonical function signature f_theta: (x_t, h_t) -> (y_t, h_{t+1}) is invariant across both, and the time-unfolded diagram represents temporal steps not spatial depth.

Justifications

SL — Architecture and configuration form independent design axes sharing a common functional interface

Antecedents (all must be IN):

IN rnn-config-vs-architecture-orthogonal — RNN configuration (data flow wiring: standard, stacked, bidirectional, encoder-decoder) and architecture (cell design: LSTM, GRU, vanilla) are orthogonal — any configuration can use any architecture.
IN rnn-standard-function-signature — A standard RNN is defined as f_θ: (x_t, h_t) → (y_t, h_{t+1}), mapping an input and hidden state to an output and updated hidden state.
IN rnn-unfolded-diagram-shows-timesteps-not-layers — Unfolding an RNN across time steps produces a diagram that resembles layers, but these represent time steps, not depth layers.