Generate Generative Data for a Data Source
Activate columns
Calculate density values for data source
Create a data source with passed data frame
Deactivate columns
Calculate inverse density value quantile
Get active column names
Get inactive column names
Get number of rows
Get a row in a data source
Read a data source from file
Write a data source to file
Generate generative data for a data source
Calculate density value for a data record
Calculate density values for generative data
Complete incomplete data record
Calculate inverse density value quantile
Calculate density value quantile
Generate generative data for a data source
Specify parameters for generation of generative data
Get number of rows
Get a row in generative data
Search for k nearest neighbors
Specify plot parameters for data source
Specify plot parameters for generative data
Create an image file for generative data and data source
Read generative data and data source
Delete a generated job from software service for accelerated training ...
Get generative data from software service for accelerated training of ...
Get generative model from software service for accelerated training of...
Get status of generated job from software service for accelerated trai...
Send a request to software service for accelerated training of generat...
Train a generative model for a data source
Specify parameters for training of generative model
Write subset of generative data
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>.