gdGenerateParameters

Specify parameters for generation of generative data. These parameters are
passed to function gdGenerate().

Generative Adversarial Networks are applied to generate generative data for a data source. A generative model consisting of a generator and a discriminator network is trained. During iterative training the distribution of generated data is converging to that of the data source. Direct applications of generative data are the created functions for data evaluation, missing data completion and data classification. A software service for accelerated training of generative models on graphics processing units is available. Reference: Goodfellow et al. (2014) <doi:10.48550/arXiv.1406.2661>.

Werner Mueller

ganGenerativeData

Generate Generative Data for a Data Source

gdGenerateParameters function

<dl><dt>numberOfSamples</dt>
<dd>Number of generated samples</dd>
<dt>dropout</dt>
<dd>Value in the range of 0 to 1. Specifies the rate of hidden
units that are dropped. Dropout is a regularization method to prevent
overfitting. See function gdTrainParameters().</dd></dl>

Arguments

Specify parameters for generation of generative data — gdGenerateParameters

<dl>

<dt>numberOfSamples</dt>
<dd>Number of generated samples</dd>


<dt>dropout</dt>
<dd>Value in the range of 0 to 1. Specifies the rate of hidden
units that are dropped. Dropout is a regularization method to prevent
overfitting. See function gdTrainParameters().</dd>

</dl>

gdGenerateParameters: Specify parameters for generation of generative data

Description

Usage

Value

Arguments

Examples