Learning

Machine learning utilities

A micro library containing the most common machine learning tools. Check also the mltool package https://hackage.haskell.org/package/mltool.

Datasets

data Dataset a b

Constructors

Dataset

Fields

• _samples :: [a]
• _labels :: [b]

Principal component analysis

data PCA

Constructors

PCA

Fields

• _u :: Matrix Double
• _compress :: Vector Double -> Matrix Double
• _decompress :: Matrix Double -> Vector Double

pca :: Int -> [Vector Double] -> PCA

Principal component analysis (PCA)

Supervised learning

type Classifier a = Matrix Double -> a

learn :: Storable a => Vector a -> Matrix Double -> Matrix Double -> Either String (Classifier a)

Perform supervised learning to create a linear classifier. The ridge regression is run with regularization parameter mu=1e-4.

learn' :: Matrix Double -> Matrix Double -> Maybe (Matrix Double)

Create a linear readout using the ridge regression

teacher :: Int -> Int -> Int -> Matrix Double

Teacher matrix

scores :: Matrix Double -> Matrix Double -> Vector Double

Evaluate the network state (nonlinear response) according to some readout matrix trW.

winnerTakesAll

Arguments

:: Storable a

=> Matrix Double

Transposed readout matrix

-> Vector a

Vector of possible classes

-> Classifier a

Classifier

Winner-takes-all classification method

Evaluation

errors :: Eq a => [(a, a)] -> [(a, a)]

Returns the misclassified cases

errorRate :: (Eq a, Fractional err) => [a] -> [a] -> err

Calculates the error rate in %