rbmUpdate

A instance of the class <code><a href="/link/?package=darch&version=0.12.0" rbm'="" data-mini-rdoc="darch::"></a>'>RBM</code>.

matMult

This function updates the weights and biases for an <code><a href="/link/?package=darch&version=0.12.0" rbm'="" data-mini-rdoc="darch::"></a>'>RBM</code> 
network. It is saved in the attribute <code>updateFunction</code> of the 
<code>RBM</code> object and called from the training function 
<code><a rd-options="" href="/link/trainRBM?package=darch&version=0.12.0" data-mini-rdoc="darch::trainRBM">trainRBM</a></code>.

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

rbmUpdate function

A instance of the class <code><a href='<a href='RBM'></a>'>RBM</a></code>.

This function updates the weights and biases for an <code><a href='<a href='RBM'></a>'>RBM</a></code> 
network. It is saved in the attribute <code>updateFunction</code> of the 
<code>RBM</code> object and called from the training function 
<code><a rd-options='' href='trainRBM'>trainRBM</a></code>.

rbmUpdate: Function for updating the weights and biases of an `RBM`

Description

Usage

Arguments

Value

See Also