rnn-config-vs-architecture-orthogonal

IN premise — entries/2026/06/21/wiki-Recurrent_neural_network-chunk-2.md

Created 2026-06-21T09:55:53+00:00

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.

Dependents

These beliefs depend on this one:

• IN rnn-design-space-two-dimensional — 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.