I am playing around with the sample codes in DiffEqFlux library of Julia here: https://github.com/SciML/DiffEqFlux.jl/blob/master/README.md#training-a-neural-ordinary-differential-equation.
function trueODEfunc(du,u,p,t)
true_A = [-0.1 2.0; -2.0 -0.1]
du .= ((u.^3)'true_A)'
end
I believe true_A is the Jacobian of the Lotka-Volterra model. Yet I do not understand the mathematical source of the u.^3 in du. Please kindly direct me or explain how the u.^3 comes about. Thank you!