The Generative Adversarial Random Neural Network - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

The Generative Adversarial Random Neural Network

Will Serrano
  • Function : Author
  • PersonId : 1105415


Generative Adversarial Networks (GANs) have been proposed as a method to generate multiple replicas from an original version combining a Discriminator and a Generator. The main applications of GANs have been the casual generation of audio and video content. GANs, as a neural method that generates populations of individuals, have emulated genetic algorithms based on biologically inspired operators such as mutation, crossover and selection. This paper presents the Generative Adversarial Random Neural Network (RNN) with the same features and functionality as a GAN: an RNN Generator produces individuals mapped from a latent space while the RNN Discriminator evaluates them based on the true data distribution. The Generative Adversarial RNN has been evaluated against several input vectors with different dimensions. The presented results are successful: the learning objective of the RNN Generator creates replicas at low error whereas the RNN Discriminator learning target identifies unfit individuals.
Embargoed file
Embargoed file
0 1 1
Year Month Jours
Avant la publication

Dates and versions

hal-03287668 , version 1 (15-07-2021)





Will Serrano. The Generative Adversarial Random Neural Network. 17th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Jun 2021, Hersonissos, Crete, Greece. pp.567-580, ⟨10.1007/978-3-030-79150-6_45⟩. ⟨hal-03287668⟩
36 View
24 Download



Gmail Facebook X LinkedIn More