newDArch

layers

batchSize

Indicates whether the <code><a href="/link/ff?package=darch&version=0.9.1&to=ff" rd-options="ff" data-mini-rdoc="ff::ff">ff</a></code>
  package is used for the weights, biases and outputs

The logging level.  See
  <code><a href="/link/setLogLevel?package=darch&version=0.9.1" rd-options="" data-mini-rdoc="darch::setLogLevel">setLogLevel</a></code> for details.

logLevel

The function for generating the
  weight matrices

genWeightFunc

Generate a new <code><a href="/link/DArch?package=darch&version=0.9.1" rd-options="" data-mini-rdoc="darch::DArch">DArch</a></code> object with the given
parameters.

The darch package is build on the basis of the code from G. E.
    Hinton and R. R. Salakhutdinov (available under Matlab Code for deep belief
    nets : last visit: 01.08.2013). This package is for generating neural
    networks with many layers (deep architectures) and train them with the
    method introduced by the publications "A fast learning algorithm for deep
    belief nets" (G. E. Hinton, S. Osindero, Y. W. Teh) and "Reducing the
    dimensionality of data with neural networks" (G. E. Hinton, R. R.
    Salakhutdinov). This method includes a pre training with the contrastive
    divergence method publishing by G.E Hinton (2002) and a fine tuning with
    common known training algorithms like backpropagation or conjugate
    gradient.

newDArch: Constructor function for `DArch` objects.

Description

Usage

Arguments

Value

Details