RealmOA Library

oa::ml::matrix::rnn_cell

Apply one Elman RNN cell update to a caller-supplied hidden state. gates_i and hidden have shape [batch, hidden], weight_hh has [hidden, hidden], and an optional recurrent bias has [hidden]. Errors Returns an error unless all values are nonempty same-engine F32 matrices, shapes agree, hidden size is at most 1024, or runtime recording fails.

FnRust public API

Function Documentation

pub fn rnn_cell( gates_i: &Matrix, hidden: &Matrix, weight_hh: &Matrix, bias_hh: Option<&Matrix> ) -> Result<Matrix>
Apply one Elman RNN cell update to a caller-supplied hidden state. gates_i and hidden have shape [batch, hidden], weight_hh has [hidden, hidden], and an optional recurrent bias has [hidden]. Errors Returns an error unless all values are nonempty same-engine F32 matrices, shapes agree, hidden size is at most 1024, or runtime recording fails.