nnf_bilinear function

Bilinear

Applies a bilinear transformation to the incoming data: $y = x_1 A x_2 + b$

nnf_bilinear(input1, input2, weight, bias = NULL)

Arguments

• input1: $(N, *, H_{in1})$ where $H_{in1}=\mbox{in1\_features}$

  and $*$ means any number of additional dimensions. All but the last dimension of the inputs should be the same.

• input2: $(N, *, H_{in2})$ where $H_{in2}=\mbox{in2\_features}$

• weight: c("$(\\mbox{out\\_features}, \\mbox{in1\\_features},\n$", "$\\mbox{in2\\_features})$")

• bias: $(\mbox{out\_features})$

Returns

output $(N, *, H_{out})$ where $H_{out}=\mbox{out\_features}$

and all but the last dimension are the same shape as the input.