RBM-class

This class represents a restricted Boltzmann machine.

internal

The darch package is built on the basis of the code from G. E.
Hinton and R. R. Salakhutdinov (available under Matlab Code for deep belief
nets). 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 (2006) <DOI:10.1162/neco.2006.18.7.1527>) and "Reducing the
dimensionality of data with neural networks" (G. E. Hinton, R. R.
Salakhutdinov (2006) <DOI:10.1126/science.1127647>). This method includes a
pre training with the contrastive divergence method published by G.E Hinton
(2002) <DOI:10.1162/089976602760128018> and a fine tuning with common known
training algorithms like backpropagation or conjugate gradients.
Additionally, supervised fine-tuning can be enhanced with maxout and
dropout, two recently developed techniques to improve fine-tuning for deep
learning.

Martin Drees

darch

Package for Deep Architectures and Restricted Boltzmann Machines

RBM-class function

<dl class="dl-horizontal">
<dt><code>weights</code></dt><dd>Object of class <code>"matrix"</code>. Weight matrix.</dd></dl><dt><code>weightsInc</code></dt><dd>Object of class <code>"matrix"</code>. Matrix of update values for 
the Weight.</dd><dt><code>visibleBiases</code></dt><dd>Object of class <code>"array"</code>. Visible biases array.</dd><dt><code>visibleBiasesInc</code></dt><dd>Object of class <code>"array"</code>. Array of update values
for the visible biases</dd><dt><code>visibleUnitStates</code></dt><dd>Object of class <code>"list"</code>. States of the visible 
units.</dd><dt><code>hiddenBiases</code></dt><dd>Object of class <code>"array"</code>. Hidden biases array.</dd><dt><code>hiddenBiasesInc</code></dt><dd>Object of class <code>"array"</code>. Array of update values 
for the hidden biases.</dd><dt><code>hiddenUnitStates</code></dt><dd>Object of class <code>"list"</code>. States of the hidden 
units.</dd><dt><code>posPhaseData</code></dt><dd>Object of class <code>"list"</code>. Attribute to save the 
positive phase data during the training.</dd><dt><code>output</code></dt><dd>Object of class <code>"matrix"</code>. Output matrix of the RBM.</dd>

RBM-class: Class for restricted Boltzmann machines

Description

Arguments

Slots

Details

See Also