# Error using ForwardDiff
**URL:** https://discourse.julialang.org/t/error-using-forwarddiff/5339
**Category:** Numerics
**Created:** [August 11, 2017, 10:13pm UTC](https://discourse.julialang.org/t/error-using-forwarddiff/5339 "2017-08-11T22:13:59Z")
**Posts on this page:** 2
**Page:** 1
### Author:  [@vgdev](https://discourse.julialang.org/u/vgdev)
#### Post date: [August 11, 2017, 10:13pm UTC](https://discourse.julialang.org/t/error-using-forwarddiff/5339/1 "2017-08-11T22:13:59Z")
Hi, I am new to ForwardDiff. However, I get an error which i cant understand why occurs.
```julia
function get_rho(a)
return sqrt(2.0*a+1.0)/(a+1.0)
end
@time ForwardDiff.gradient(a ->get_rho(a), -0.43)
```
From the code above I get the following error:
> MethodError: Cannot `convert` an object of type Float64 to an object of type ForwardDiff.GradientConfig
> This may have arisen from a call to the constructor ForwardDiff.GradientConfig(…),
> since type constructors fall back to convert methods.
> gradient(::##23#24, ::Float64) at gradient.jl:6
> include\_string(::String, ::String) at loading.jl:515
> include\_string(::String, ::String, ::Int64) at eval.jl:30
> include\_string(::Module, ::String, ::String, ::Int64, ::Vararg{Int64,N} where N) at eval.jl:34
> (::Atom.##49#52{String,Int64,String})() at eval.jl:50
> withpath(::Atom.##49#52{String,Int64,String}, ::String) at utils.jl:30
> withpath(::Function, ::String) at eval.jl:38
> macro expansion at eval.jl:49 [inlined]
> (::Atom.##48#51{Dict{String,Any}})() at task.jl:80
Any help with this, will be highly appreciated 🙂
---
### Author:  [@aaowens](https://discourse.julialang.org/u/aaowens)
#### Post date: [August 11, 2017, 10:32pm UTC](https://discourse.julialang.org/t/error-using-forwarddiff/5339/2 "2017-08-11T22:32:20Z")
`gradient` is for multivariate functions. You can use `derivative`. Also, the anonymous function is unnecessary here.
This works:
```julia
julia> @time ForwardDiff.derivative(get_rho, -0.43)
0.000007 seconds (5 allocations: 176 bytes)
3.537160173048399
```