rbm.train: Training a RBM(restricted Boltzmann Machine)

Description Usage Arguments Author(s) Examples

View source: R/rbm.R

Description

Training a RBM(restricted Boltzmann Machine)

Usage

1
2
3
4
rbm.train(x, hidden, numepochs = 3, batchsize = 100, learningrate = 0.8,
  learningrate_scale = 1, momentum = 0.5, visible_type = "bin",
  hidden_type = "bin", cd = 1, verbose = F, keep.data = F,
  model = NULL)

Arguments

x

matrix of x values for examples

hidden

number of hidden units

numepochs

number of iteration for samples Default is 3.

batchsize

size of mini-batch. Default is 100.

learningrate

learning rate for gradient descent. Default is 0.8.

learningrate_scale

learning rate will be mutiplied by this scale after every iteration. Default is 1 .

momentum

momentum for gradient descent. Default is 0.5 .

visible_type

activation function of input unit.Only support "sigm" now

hidden_type

activation function of hidden unit.Only support "sigm" now

cd

number of iteration for Gibbs sample of CD algorithm.

verbose

print a string for each epoch done

keep.data

keep the weight for each epoch, usefull for DPE

Author(s)

Xiao Rong

Examples

1
2
3
4
Var1 <- c(rep(1,50),rep(0,50))
Var2 <- c(rep(0,50),rep(1,50))
x3 <- matrix(c(Var1,Var2),nrow=100,ncol=2)
r1 <- rbm.train(x3,10,numepochs=20,cd=10)

DimitriF/DLC documentation built on March 21, 2018, 8:49 p.m.