Generative adversarial network- GANs

Concept and definition

Generative adversarial network- GANs

What is Generative adversarial network- GANs?

The generator is usually a multilayer perceptron (neural network made up of multiple layers) and its goal is to create data as close as possible to real data in order to fool the discriminator when it evaluates them.

The generator is usually a multilayer perceptron (neural network made up of multiple layers) and its objective is to create data as close as possible to real data in order to deceive the discriminator when it evaluates them.

The discriminator is usually a convolutional neural network, in charge of classifying incoming data as real or not, assigning each one a probability of being real. In the training phase of the neural network, the discriminator will receive both data generated by the generator and data belonging to a training set, and tries to distinguish between them.

« Back to glossary

Do you want to get in touch?

CDRs contain data that a telecommunications company collects about phone calls, such as time and length of call. This data can be used in analytical applications.
Fill the form
Share:
Cloud solutions for SMEs

Cloud computing services or solutions are software infrastructures, platforms or systems that are hosted by external service providers.

Read More »
How to detect delinquent customers and avoid defaults? 10 signs of delinquency

As a consequence of this pandemic and economic situation in which we have found ourselves for the last two years, with the intention of better protecting the [...]

Read More »
Clustering for data analysis

Clustering methods, or grouping, are a fundamental part of the data analysis process, since they allow an automatic segmentation of the data [...]

Read More »
How AI models attract potential customers

The acquisition of new potential customers is one of the most important and difficult processes for a company. Traditionally, it has been necessary to [...]

Read More »
See more entries
© Gamco 2021, All Rights Reserved - Legal notice - Privacy - Cookies