GRUBlockCellGrad

w_ru = [w_r_x w_u_x
         w_r_h_prev w_u_h_prev]
 

w_c = [w_c_x w_c_h_prevr]
 

b_ru = [b_ru_x b_ru_h]
 b_c = [b_c_x b_c_h]
 

d_x = d_x_component_1 + d_x_component_2
 
 where d_x_component_1 = d_r_bar * w_r_x^T + d_u_bar * w_r_x^T
 and d_x_component_2 = d_c_bar * w_c_x^T
 
 d_h_prev = d_h_prev_component_1 + d_h_prevr \circ r + d_h \circ u
 where d_h_prev_componenet_1 = d_r_bar * w_r_h_prev^T + d_u_bar * w_r_h_prev^T
 

d_c_bar = d_h \circ (1-u) \circ (1-c \circ c)
 d_u_bar = d_h \circ (h-c) \circ u \circ (1-u)
 
 d_r_bar_u_bar = [d_r_bar d_u_bar]
 
 [d_x_component_1 d_h_prev_component_1] = d_r_bar_u_bar * w_ru^T
 
 [d_x_component_2 d_h_prevr] = d_c_bar * w_c^T
 
 d_x = d_x_component_1 + d_x_component_2
 
 d_h_prev = d_h_prev_component_1 + d_h_prevr \circ r + u
 

d_w_ru = x_h_prevr^T * d_c_bar
 
 d_w_c = x_h_prev^T * d_r_bar_u_bar
 
 d_b_ru = sum of d_r_bar_u_bar along axis = 0
 
 d_b_c = sum of d_c_bar along axis = 0