v0.8.0

KernelFunctions v0.8.0

Diff since v0.7.2

Merged pull requests:

• [WIP] Fix AD issues with various kernels (#154) (@sharanry)
• Fix SqExponential and GammaExponential + style (#158) (@willtebbutt)

v0.7.2

KernelFunctions v0.7.2

Diff since v0.7.1

Merged pull requests:

• Add Latent-factor multi-output kernel (#143) (@sharanry)

v0.7.1

KernelFunctions v0.7.1

Diff since v0.7.0

Closed issues:

• AD issue with mixed inputs (#151)

Merged pull requests:

• Fix AD issue with mixed input for TransformedKernel (#160) (@sharanry)
• Add style guide (#161) (@willtebbutt)

v0.7.0

KernelFunctions v0.7.0

Diff since v0.6.1

Merged pull requests:

• Use Functors (#157) (@devmotion)

v0.6.1

KernelFunctions v0.6.1

Diff since v0.6.0

Closed issues:

• Mahalabonis constructor is not given by keyword (#64)
• Refactor KernelSum and KernelProduct? (#68)
• Using mapslices for FunctionTransform make it incompatible with Zygote (#74)

Merged pull requests:

• Replace constructor of Maha with keyword one (#126) (@theogf)
• Fix Zygote issues with FunctionTransform (#152) (@sharanry)
• SelectTransform extended to Symbols (#155) (@molet)
• Add ColPrac to README (#156) (@willtebbutt)

v0.6.0

KernelFunctions v0.6.0

Diff since v0.5.1

v0.5.1

KernelFunctions v0.5.1

Diff since v0.5.0

Closed issues:

• Make validate_dims opt-in (#139)
• Removing BaseKernel (#149)

Merged pull requests:

• Use tuples in KernelSum and KernelProduct; Make Zygote tests pass for KernelSum and KernelProduct; Improve doctring. (#146) (@sharanry)

v0.5.0

KernelFunctions v0.5.0

Diff since v0.4.5

Merged pull requests:

• Input check relaxation and change of `pairwise (#147) (@theogf)

v0.4.5

KernelFunctions v0.4.5

Diff since v0.4.4

Merged pull requests:

• Test stable Julia version (#148) (@devmotion)
• Remove BaseKernel and deprecated functions (#150) (@theogf)

v0.4.4

KernelFunctions v0.4.4

Diff since v0.4.3

Closed issues:

• Implicit gradient failing with matrices (#137)

Merged pull requests:

• Fixing implicit gradients (#141) (@theogf)
• Fix Independent MOKernel for single dimension input (#144) (@sharanry)
• Enforce 'Tuple{Any, Int}' type inputs for IndependentMOKernel (#145) (@sharanry)