NMSISNN
Version 1.2.0
NMSIS NN Software Library

z[t] = sigmoid( W_z ⋅ {h[t1],x[t]} ) r[t] = sigmoid( W_r ⋅ {h[t1],x[t]} ) n[t] = tanh( W_n ⋅ [r[t] × {h[t1], x[t]} ) h[t] = (1  z[t]) × h[t1] + z[t] × n[t]
update_gate_weights
, reset_gate_weights
, hidden_state_weights
are weights corresponding to update gate (W_z), reset gate (W_r), and hidden state (W_n). update_gate_bias
, reset_gate_bias
, hidden_state_bias
are layer bias arrays test_input1
, test_input2
, test_history
are the inputs and initial historyRefer riscv_nnexamples_gru.cpp