v5.16.0

NeuralPDE v5.16.0

Diff since v5.15.0

Merged pull requests:

• chore: format the whole repo (#841) (@sathvikbhagavan)
• build(deps): bump julia-actions/setup-julia from 1 to 2 (#843) (@dependabot[bot])
• ci: add NNODE, NeuralAdapter, IntegroDiff in GHA from buildkite to have them in Downgrade CI (#845) (@sathvikbhagavan)
• Tag the original solution to sol.original and simplify dependencies (#846) (@ChrisRackauckas)

Closed issues:

• Neural Adaptor tests set as @test_broken (#513)
• Multithreaded test suite (#706)
• Add support for equations with complex numbers (#821)

v5.15.0

NeuralPDE v5.15.0

Diff since v5.14.0

Merged pull requests:

• build: bump mtk to v9 (#828) (@sathvikbhagavan)
• ci: add Downgrade CI (#831) (@sathvikbhagavan)
• docs: fix rendering (#832) (@sathvikbhagavan)
• refactor: correctly lower quadrature training strategy in NNODE (#836) (@sathvikbhagavan)
• feat: allow complex for NNODE (#839) (@sathvikbhagavan)

Closed issues:

• Allow batching with QuadratureStrategy in NNODE (#555)

v5.14.0

NeuralPDE v5.14.0

Diff since v5.13.0

Merged pull requests:

• docs: update and cleanup tutorials and examples (#815) (@sathvikbhagavan)

Closed issues:

• Neural Adapter Documentation Example Not Working (#824)

v5.13.0

NeuralPDE v5.13.0

Diff since v5.12.0

Merged pull requests:

• build(deps): bump codecov/codecov-action from 3 to 4 (#800) (@dependabot[bot])
• add Deep Galerkin method (#802) (@ayushinav)
• fix: bounds of variables in neural adapter setup (#812) (@sathvikbhagavan)
• CompatHelper: bump compat for DomainSets to 0.7, (keep existing compat) (#813) (@github-actions[bot])
• CompatHelper: bump compat for DomainSets to 0.7 for package docs, (keep existing compat) (#814) (@github-actions[bot])
• ci: explicitly specify token for codecov (#819) (@sathvikbhagavan)
• refactor: use latest API for IntegralProblem (#822) (@sathvikbhagavan)
• build(deps): bump crate-ci/typos from 1.18.2 to 1.19.0 (#823) (@dependabot[bot])
• chore: format docstrings of DGM to make it consistent with others (#825) (@sathvikbhagavan)
• reducing test times for DGM (#826) (@ayushinav)

Closed issues:

• Deep learning methods for free-boundary PDEs (#19)
• Deep Galerkin Method (#220)
• DGM Tutorial fails (#827)

v5.12.0

NeuralPDE v5.12.0

Diff since v5.11.0

Merged pull requests:

• Bump AdvancedHMC (#804) (@ChrisRackauckas)
• build(deps): bump crate-ci/typos from 1.18.0 to 1.18.2 (#805) (@dependabot[bot])
• fix: tstops loss in NNODE (#807) (@sathvikbhagavan)
• refactor: loss functions for NNODE (#808) (@sathvikbhagavan)
• build: bump Optimization packages and use only latest versions for all (#809) (@sathvikbhagavan)

Closed issues:

• NN ODE loss gets squared (#606)
• Problem in replicating INVERSE PROBELM tutorial on ODE (#765)
• Bump CUDA Compat (#810)

v5.11.0

NeuralPDE v5.11.0

Diff since v5.10.0

Merged pull requests:

• Bump actions/cache from 3 to 4 (#787) (@dependabot[bot])
• Remove duplicated methods in BPINN as it causes methods overwrite (#788) (@sathvikbhagavan)
• Remove Flux Support (#789) (@sathvikbhagavan)
• DAE problem (#790) (@KirillZubov)
• feat: add Parameter estimation capability in NNODE (#795) (@sathvikbhagavan)
• Add QA (#796) (@sathvikbhagavan)
• ci: add spell check workflow (#797) (@sathvikbhagavan)
• build(deps): bump crate-ci/typos from 1.17.0 to 1.18.0 (#801) (@dependabot[bot])

Closed issues:

• Recreate the examples from the BINN paper with NNODE (#640)
• Issue with NNStopping Example code (#680)
• NeuralPDE v.5.9 stops QuasiMonteCarlo from updating (#748)
• Parameter Estimation in NNODE (#766)

v5.10.0

NeuralPDE v5.10.0

Diff since v5.9.0

Merged pull requests:

• Docs modifications to use QuadratureTraining instead of GridTraining (#729) (@sdesai1287)
• Documenter 1.0 upgrade (#739) (@ArnoStrouwen)
• changes from final reviews, improved Docs (#741) (@AstitvaAggarwal)
• Remove v1.6 from CI (#743) (@ChrisRackauckas)
• BPINN PDE solver (#745) (@AstitvaAggarwal)
• ci: run Documentation builds on buildkite instead of GHA (#750) (@thazhemadam)
• build: make optim version >= 1.7.8 (#753) (@sathvikbhagavan)
• ci(buildkite): fix GPU tests not being run on Buildkite (#756) (@thazhemadam)
• Refactor/cleanup ode tutorials (#757) (@sathvikbhagavan)
• BNNODE bug fix, faster MvNormal pdf definition (#760) (@AstitvaAggarwal)
• Fix typo "simultaniously" -> "simultaneously" (#763) (@brollb)
• CompatHelper: add new compat entry for Statistics at version 1, (keep existing compat) (#764) (@github-actions[bot])
• Change typeof(x) <: y to x isa y (#767) (@pepijndevos)
• Fix ODE tutorial link (#771) (@bowenszhu)
• CompatHelper: bump compat for Adapt to 4, (keep existing compat) (#775) (@github-actions[bot])
• version 1.9 to dodge compat bump bandwagon (#776) (@AstitvaAggarwal)
• BPINN solver Docs(Manual and tutorial) (#781) (@AstitvaAggarwal)
• build: compat bumps to latest versions (#783) (@sathvikbhagavan)
• build: remove >= for Optim compat. (#786) (@sathvikbhagavan)

Closed issues:

• Migrate functionality to HighDimPDE.jl (#514)
• NNODE fails on simple logistic curve (#634)
• Bayesian Inference for PDE PINN solver (#712)
• fix NUTS kwargs handling and Default ode params vector (#737)
• BNNODE dosent support Lux chains Initparams, supporting fix for PR #749 (#759)
• Documentation for BayesianPINN and ahmc_bayesian_pinn_pde (#779)
• Encountering Precompilation Error Messages When Adding NeuralPDE Package in Julia (#780)

v5.9.0

NeuralPDE v5.9.0

Diff since v5.8.0

Merged pull requests:

• [WIP] Bayesian PINN solver for ODE (#692) (@AstitvaAggarwal)
• Fix ODEs system and add test (#714) (@KirillZubov)
• CompatHelper: add new compat entry for Functors at version 0.4, (keep existing compat) (#715) (@github-actions[bot])
• CompatHelper: add new compat entry for MCMCChains at version 6, (keep existing compat) (#716) (@github-actions[bot])
• CompatHelper: add new compat entry for LogDensityProblems at version 2, (keep existing compat) (#717) (@github-actions[bot])
• CompatHelper: add new compat entry for AdvancedHMC at version 0.5, (keep existing compat) (#718) (@github-actions[bot])
• Incorporating given points into training (#723) (@sdesai1287)
• [WIP] API for BNNODE (#724) (@AstitvaAggarwal)
• CompatHelper: bump compat for Optimisers to 0.3, (keep existing compat) (#726) (@github-actions[bot])
• Rename samples field of WeightedIntervalTraining to points and clean tstops_loss logic (#727) (@sathvikbhagavan)
• Bump actions/checkout from 3 to 4 (#730) (@dependabot[bot])
• CompatHelper: bump compat for ComponentArrays to 0.15, (keep existing compat) (#732) (@github-actions[bot])
• CompatHelper: add new compat entry for MonteCarloMeasurements at version 1, (keep existing compat) (#736) (@github-actions[bot])
• CompatHelper: bump compat for SciMLBase to 2, (keep existing compat) (#738) (@github-actions[bot])

Closed issues:

• Have a training strategy for PreDefined Points (#644)
• Bayesian Inference for NNODE (#682)
• Type issue in Julia v1.9 (#696)
• Adaptive reweighting or modify neural network to solve complex system. (#708)
• Issued with sin and cos function after update version of NeuralPDE (#710)
• API for BNNODE. (#719)
• one-dimensional heat equation (#720)

v5.8.0

NeuralPDE v5.8.0

Diff since v5.7.0

Closed issues:

• Parameters estimation using NeuralPDE.jl is not working for PDEs (#681)
• Demo not running (#690)
• Parameters estimation using NeuralPDE.jl is not working for PDEs (#694)
• Failed to precompile NeuralPDE (#698)
• Precompilation warning (#709)

Merged pull requests:

• CompatHelper: bump compat for ComponentArrays to 0.14, (keep existing compat) (#699) (@github-actions[bot])
• CompatHelper: bump compat for Flux to 0.14, (keep existing compat) (#700) (@github-actions[bot])
• CompatHelper: bump compat for Flux to 0.14 for package docs, (keep existing compat) (#701) (@github-actions[bot])
• CompatHelper: bump compat for Lux to 0.5, (keep existing compat) (#704) (@github-actions[bot])
• CompatHelper: bump compat for Lux to 0.5 for package docs, (keep existing compat) (#705) (@github-actions[bot])

v5.7.0

NeuralPDE v5.7.0

Diff since v5.6.1

Closed issues:

• Push nnode further (#46)
• Treating states properly, second encounter (#605)

Merged pull requests:

• Explored some new training strategies for large neural networks. (#635) (@sdesai1287)
• added additional loss against data for NNODE (#666) (@AstitvaAggarwal)
• Try domainsets v0.6 (#675) (@ChrisRackauckas)
• Test new DiffEqBase (#676) (@ChrisRackauckas)
• fix formatting (#677) (@ChrisRackauckas)