Safe Haskell | None |
---|---|
Language | Haskell2010 |
A version of Sparse
extended with momentum.
Documentation
SGD parameters controlling the learning process.
sgdArgsDefault :: SgdArgs Source #
Default SGD parameter values.
:: SgdArgs | SGD parameter values |
-> (Para -> Int -> IO ()) | Notification run every update |
-> (Para -> x -> Grad) | Gradient for dataset element |
-> DataSet x | DataSet |
-> Para | Starting point |
-> IO Para | SGD result |
A stochastic gradient descent method. A notification function can be used to provide user with information about the progress of the learning.
module Numeric.SGD.Sparse.Grad
module Numeric.SGD.DataSet