I’m wondering if I `Flux.jl`

can be used to construct a multi layer CES function. I won’t be training the function in Flux, just leverage its multi layer flexibility. For example, consider the function

where x and a are vectors of length n, and \rho is a scalar. a and \rho represent parameters, and x represents inputs. In turn, each x_i can possibly be also composed of other layers:

for parameters b, r and inputs y.

Can that be accommodated in `Flux.jl`

?