grenade-0.1.0: Practical Deep Learning in Haskell

Safe HaskellNone
LanguageHaskell98

Grenade.Recurrent.Core.Runner

Synopsis

Documentation

trainRecurrent :: forall shapes layers. (SingI (Last shapes), Num (RecurrentInputs layers)) => LearningParameters -> RecurrentNetwork layers shapes -> RecurrentInputs layers -> [(S (Head shapes), Maybe (S (Last shapes)))] -> (RecurrentNetwork layers shapes, RecurrentInputs layers) Source #

runRecurrent :: RecurrentNetwork layers shapes -> RecurrentInputs layers -> S (Head shapes) -> (RecurrentInputs layers, S (Last shapes)) Source #

Just forwards propagation with no training.

backPropagateRecurrent :: forall shapes layers. (SingI (Last shapes), Num (RecurrentInputs layers)) => RecurrentNetwork layers shapes -> RecurrentInputs layers -> [(S (Head shapes), Maybe (S (Last shapes)))] -> (RecurrentGradients layers, RecurrentInputs layers) Source #

Drive and network and collect its back propogated gradients.