API Docs for: 0.0.1
Show:

DBN Class

Defined in: lib/DBN.js:19
Module: n42

Deep Belief Nets

Constructor

DBN

()

Defined in lib/DBN.js:19

Item Index

Properties

Methods

predict

(
  • x
)

Defined in lib/DBN.js:147

Predict label with training data

Parameters:

  • x Matrix

    input data

pretrain

(
  • lr
  • k
  • epochs
)

Defined in lib/DBN.js:101

Training hidden layers with unsupervised learning

Parameters:

  • lr Float

    learning rate

  • k Int

    the number of phase

  • epochs Int

    the number of times of running gradient decent

train

(
  • lr
  • epochs
)

Defined in lib/DBN.js:130

Training logistics regression algorithm which is on output layer

Parameters:

  • lr Float

    learning rate

  • epochs Int

    the number of times of running gradient decent

Properties

nLayers

Int

Defined in lib/DBN.js:53

number of hidden layers

sigmoidLayers

Array

Defined in lib/DBN.js:43

hidden layers which activations are sigmoid function

x

Matrix

Defined in lib/DBN.js:29

input data. This type is defined in sylvester library

y

Matrix

Defined in lib/DBN.js:36

label data. This type is defined in sylvester library