v0.2.8

Sophon v0.2.8

Diff since v0.2.7

Merged pull requests:

• CompatHelper: add new compat entry for RuntimeGeneratedFunctions at version 0.5, (keep existing compat) (#157) (@github-actions[bot])

v0.2.7

Sophon v0.2.7

Diff since v0.2.6

Merged pull requests:

• Update componentarrays.jl (#155) (@YichengDWu)
• Clean up (#156) (@YichengDWu)

v0.2.6

Sophon v0.2.6

Diff since v0.2.5

Closed issues:

• Change LBFGS to BFGS (#150)
• remove device_type in favor of gpu and cpu (#152)

Merged pull requests:

• Create Inverse.md (#151) (@Runfa-Zhang)
• Remove 'device_type` and lock the precision of FD to Float64 (#153) (@YichengDWu)

v0.2.5

Sophon v0.2.5

Diff since v0.2.4

v0.2.4

Sophon v0.2.4

Diff since v0.2.3

Closed issues:

• Tutorials (#19)
• interface for adaptive sampling (#119)

Merged pull requests:

• Custom sampling (#148) (@YichengDWu)
• Rename Scalar to ConstantFunction (#149) (@YichengDWu)

v0.2.3

Sophon v0.2.3

Diff since v0.2.2

Closed issues:

• PINN should allow seeding (#131)
• Sample one dataset for all equations (#137)

Merged pull requests:

• Create Schrödinger equation.md (#136) (@Runfa-Zhang)
• Allow seeding for PINN (#144) (@YichengDWu)
• Sample one dataset for all PDEs (#145) (@YichengDWu)
• Change CairoMakie to GLMakie (#146) (@YichengDWu)
• Introduce Adaptiveloss (#147) (@YichengDWu)

v0.2.2

Sophon v0.2.2

Diff since v0.2.1

Closed issues:

• get_bounds should return a vector of lower bounds and upper bounds (#135)
• rewrite QuasiSampler (#138)

Merged pull requests:

• Fix name conflicts of SplitFunction (#132) (@YichengDWu)
• change the default sampling alg to sobol (#133) (@YichengDWu)
• Revert "change the default sampling alg to sobol" (#134) (@YichengDWu)
• Generate (lbs, ubs) for each equation and use SobolSample as default (#139) (@YichengDWu)
• Fix get_bounds (#140) (@YichengDWu)
• CompatHelper: add new compat entry for Memoize at version 0.4, (keep existing compat) (#141) (@github-actions[bot])
• CompatHelper: add new compat entry for Sobol at version 1, (keep existing compat) (#142) (@github-actions[bot])
• CompatHelper: add new compat entry for LRUCache at version 1, (keep existing compat) (#143) (@github-actions[bot])

v0.2.1

Sophon v0.2.1

Diff since v0.2.0

Closed issues:

• Nibbling NeuralPDE (#111)

Merged pull requests:

• rename Scalar to Scalarlayer and add Scalar as a constant function (#130) (@YichengDWu)

v0.2.0

Sophon v0.2.0

Diff since v0.1.9

Closed issues:

• introduce scalarize to scalarize loss functions (#123)

Merged pull requests:

• Separate PDE and Sampler (#127) (@YichengDWu)
• sample a vector of datasets (#128) (@YichengDWu)
• Allen-Cahn Equation with sequential training (#129) (@YichengDWu)

v0.1.9

Sophon v0.1.9

Diff since v0.1.8

Merged pull requests:

• Better timesteps for different orders (#125) (@YichengDWu)
• using modelingtoolkit (#126) (@YichengDWu)