| Copyright | (c) Lars Brünjes, 2016 |
|---|---|
| License | MIT |
| Maintainer | brunjlar@gmail.com |
| Stability | experimental |
| Portability | portable |
| Safe Haskell | None |
| Language | Haskell2010 |
| Extensions | BangPatterns |
Numeric.Neural.Pipes
Description
This modules provides a "pipes"-based API for working with models.
- data TS f g a b c = TS {
- tsModel :: Model f g a b c
- tsGeneration :: Int
- tsEta :: Double
- tsBatchError :: Double
- descentP :: (Foldable h, Monad m) => Model f g a b c -> Int -> (Int -> Double) -> Pipe (h a) (TS f g a b c) m r
- simpleBatchP :: MonadRandom m => [a] -> Int -> Producer [a] m r
- reportTSP :: Monad m => Int -> (TS f g a b c -> m ()) -> Pipe (TS f g a b c) (TS f g a b c) m r
- consumeTSP :: Monad m => (TS f g a b c -> m (Maybe x)) -> Consumer (TS f g a b c) m x
- module Pipes
Documentation
The training state of a model.
Constructors
| TS | |
Fields
| |
Arguments
| :: (Foldable h, Monad m) | |
| => Model f g a b c | initial model |
| -> Int | first generation |
| -> (Int -> Double) | computes the learning rate from the generation |
| -> Pipe (h a) (TS f g a b c) m r |
A Pipe for training a model: It consumes mini-batches of samples from upstream and pushes
the updated training state downstream.
Arguments
| :: MonadRandom m | |
| => [a] | all available samples |
| -> Int | the mini-batch size |
| -> Producer [a] m r |
A simple Producer of mini-batches.
Arguments
| :: Monad m | |
| => Int | report interval |
| -> (TS f g a b c -> m ()) | report action |
| -> Pipe (TS f g a b c) (TS f g a b c) m r |
A Pipe for progress reporting of model training.
Arguments
| :: Monad m | |
| => (TS f g a b c -> m (Maybe x)) | check whether training is finished and what to return in that case |
| -> Consumer (TS f g a b c) m x |
A Consumer of training states that decides when training is finished and then returns a value.
module Pipes