The Exponential kernel class.
Note that it can handle a length scale for each dimension for Automtic Relevance Determination.
Methods
add_conversion(typename, methodfull, methodraw) | Adds methods to the Kernel class for new conversions |
as_ls(kernel) | |
as_np() | Converts this kernel to a Numpy-based representation |
as_raw_ls(kernel) | |
as_raw_np() | Directly return this kernel as a numpy array. |
cleanup() | Wipe out internal representation |
compute(ds1[, ds2]) | Generic computation of any kernel |
compute_lml_gradient(alphaalphaT_Kinv, data) | Compute grandient of the kernel and return the portion of log marginal likelihood gradient due to the kernel. |
compute_lml_gradient_logscale(...) | Compute grandient of the kernel and return the portion of log marginal likelihood gradient due to the kernel. |
computed(*args, **kwargs) | Compute kernel and return self |
gradient(data1, data2) | Compute gradient of the kernel matrix. |
reset() |
Initialize instance of ExponentialKernel
Parameters: | length_scale :
sigma_f :
enable_ca : None or list of str
disable_ca : None or list of str
|
---|
Methods
add_conversion(typename, methodfull, methodraw) | Adds methods to the Kernel class for new conversions |
as_ls(kernel) | |
as_np() | Converts this kernel to a Numpy-based representation |
as_raw_ls(kernel) | |
as_raw_np() | Directly return this kernel as a numpy array. |
cleanup() | Wipe out internal representation |
compute(ds1[, ds2]) | Generic computation of any kernel |
compute_lml_gradient(alphaalphaT_Kinv, data) | Compute grandient of the kernel and return the portion of log marginal likelihood gradient due to the kernel. |
compute_lml_gradient_logscale(...) | Compute grandient of the kernel and return the portion of log marginal likelihood gradient due to the kernel. |
computed(*args, **kwargs) | Compute kernel and return self |
gradient(data1, data2) | Compute gradient of the kernel matrix. |
reset() |
Compute grandient of the kernel and return the portion of log marginal likelihood gradient due to the kernel. Shorter formula. Allows vector of lengthscales (ARD) BUT THIS LAST OPTION SEEMS NOT TO WORK FOR (CURRENTLY) UNKNOWN REASONS.
Compute grandient of the kernel and return the portion of log marginal likelihood gradient due to the kernel. Shorter formula. Allows vector of lengthscales (ARD). BUT THIS LAST OPTION SEEMS NOT TO WORK FOR (CURRENTLY) UNKNOWN REASONS.
Compute gradient of the kernel matrix. A must for fast model selection with high-dimensional data.