initializer_glorot_uniform

It draws samples from a uniform distribution within <code>-limit, limit</code>
where <code>limit</code> is <code>sqrt(6 / (fan_in + fan_out))</code>
where <code>fan_in</code> is the number of input units in the weight tensor
and <code>fan_out</code> is the number of output units in the weight tensor.

Interface to 'Keras' <https://keras.io>, a high-level neural
networks 'API'. 'Keras' was developed with a focus on enabling fast experimentation,
supports both convolution based networks and recurrent networks (as well as
combinations of the two), and runs seamlessly on both 'CPU' and 'GPU' devices.

Tomasz Kalinowski

keras

R Interface to 'Keras'

Daniel Falbel

JJ Allaire

François Chollet

RStudio 

Google 

Yuan Tang

Wouter Van Der Bijl

Martin Studer

Sigrid Keydana

initializer_glorot_uniform function

<dl><dt>seed</dt>
<dd>Integer used to seed the random generator.</dd></dl>

Arguments

Glorot uniform initializer, also called Xavier uniform initializer. — initializer_glorot_uniform

<dl>

<dt>seed</dt>
<dd>Integer used to seed the random generator.</dd>

</dl>

Glorot uniform initializer, also called Xavier uniform initializer.

initializer_glorot_uniform: Glorot uniform initializer, also called Xavier uniform initializer.

Description

Usage

Arguments

References

See Also