generateWeightsGlorotUniform

Number of units in the lower layer.

numUnits1

Number of units in the upper layer.

numUnits2

Additional parameters, used for parameter resolution and passed
to <code><a rd-options="" href="/link/generateWeightsUniform?package=darch&version=0.12.0" data-mini-rdoc="darch::generateWeightsUniform">generateWeightsUniform</a></code>.

This function is used to generate random weights and biases using
Glorot uniform weight initialization as described in
Glorot &amp; Bengio, AISTATS 2010.

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

generateWeightsGlorotUniform function

Additional parameters, used for parameter resolution and passed
to <code><a rd-options='' href='generateWeightsUniform'>generateWeightsUniform</a></code>.

generateWeightsGlorotUniform: Glorot uniform weight initialization

Description

Usage

Arguments

Value

References

See Also

Examples