New loss #937
New loss #937
Conversation
|
@ChrisRackauckas i think there are some compat issues in the Downgrade Test env. |
|
Yes don't worry about downgrade |
|
@ChrisRackauckas the following PR adds the new loss for NNODE and BNNODE (with appropriate tests) and corrects tests erroring out in BPINN_PDE_tests.jl (this started once the repo was completely overhauled). Just to give some insight, BPINN model performance for just 20 training points in t=(0,4) as in the tests added where we solve LV : u2 is our new model. |
Co-authored-by: Christopher Rackauckas <[email protected]>
|
@ChrisRackauckas GTM? |
| priors <: Vector{<:Distribution} | ||
| phystd::Vector{Float64} | ||
| phynewstd::Vector{Float64} | ||
| phynewstd::Function |
There was a problem hiding this comment.
im not sure how we can specialize functions...
(Im keeping a function for std in BPINNs as selecting the right std can be tricky and usually depends on the problem)
| * `strategy`: The training strategy used to choose the points for the evaluations. | ||
| Default of `nothing` means that `QuadratureTraining` with QuadGK is used if no | ||
| `dt` is given, and `GridTraining` is used with `dt` if given. | ||
| * `estim_collocate`: A boolean value to indicate whether to use the new loss function or not. This is only relevant for ODE parameter estimation. |
There was a problem hiding this comment.
need a more descriptive name than "the new loss function" lol
There was a problem hiding this comment.
Will change that, im trying to be lowkey as it's all open source haha
|
The BPINN tests need some tweaking. But this looks fine. Follow up with doc improvements. |
|
Do you mean the BPINN pde solvers tests? Ive actually corrected the tests as previously tests were erroring out (ever since the overhaul format), now I'll fix the failures. |
2 participants
Checklist
contributor guidelines, in particular the SciML Style Guide and
COLPRAC.
tutorial on how to use newloss and updated PINO must be added in a New PR