I’m trying to add inequality constraints to my ODE parameter optimization problem. The example I followed was fluxdiffeq . I need p[1] + p[2] <= 1 and p[1] and p[2] both also have to be positive. Is there any way I can achieve this with DiffEqFlux?

[image] RuoyuWang72: MethodError: Cannot convert an object of type Vector{Vector{Float64}} to an object of type Float64. Objective functions need to output a scalar cost value. sol_.u .- sol.u is a Vector{Float64} for the loss of each value at each time point. Did you instead mean sum(abs2,Ar…

ODE parameter estimation using neural nets

Specific Domains

ChrisRackauckas September 21, 2022, 6:54am 6

Objective functions need to output a scalar cost value. sol_.u .- sol.u is a Vector{Float64} for the loss of each value at each time point. Did you instead mean sum(abs2,Array(sol_) .- Array(sol))?

Topic		Replies	Views
NeuralODE: optimal control action in a constrained optimization problem Machine Learning diffeq , flux , optimization , machine-learning , neural-network	13	2119	July 26, 2021
NeuralODE Loss function constrain optimization General Usage package , diffeq , optimization , neural-network , differentialequation	19	683	March 18, 2023
Error in parameter estimation of ODEs New to Julia	7	318	October 17, 2022
Optim.jl violates inequality constraint Optimization (Mathematical) optim	3	899	February 4, 2022
Domain Troubles with Differential Equations Solver (with non-auto-differentiable function inside the ODE def) Numerics question , diffeq	33	3585	August 19, 2018

ODE parameter estimation using neural nets

Related topics