2.1.2
Simplified version of the Sequential Minimal Optimization algorithm for training support vector machines
([object])
SVM options
Name | Description |
---|---|
options.C [number]
(default 1 )
|
regularization parameter |
options.tol [number]
(default 1e-4 )
|
numerical tolerance |
options.alphaTol [number]
(default 1e-6 )
|
alpha tolerance, threshold to decide support vectors |
options.maxPasses [number]
(default 10 )
|
max number of times to iterate over alphas without changing |
options.maxIterations [number]
(default 10000 )
|
max number of iterations |
options.kernel [string]
(default linear )
|
the kind of kernel. List of kernels |
options.random [function]
(default Math.random )
|
custom random number generator |