Deep neural network representation and Generative Adversarial Learning

ARIEL RUIZ-GARCIA, Jürgen Schmidhuber, VASILE PALADE, Clive Cheong Took, Danilo Mandic

Research output: Contribution to journalEditorialpeer-review

40 Downloads (Pure)

Abstract

Generative Adversarial Networks (GANs) have proven to be efficient systems for data generation and other machine learning tasks. They owe their success to a minimax learning concept initially proposed by Schmidhuber (1990) to implement Artificial Curiosity. Two learning networks, a generator and an evaluator or discriminator, compete with each other in a zero-sum game. Despite their obvious advantages and their application to a wide range of domains, GANs have yet to overcome several challenges such as non-convergence, overfitting, mode collapse, amongst others. New advancements in deep representation learning (RL) can help improve the learning process in GenerativeAdversarial Learning (GAL). For instance, RL can help address issues such as dataset bias and identify a set of features that are well suited for a given task.
Original languageEnglish
Pages (from-to)1-2
Number of pages2
JournalNeural Networks
DOIs
Publication statusE-pub ahead of print - 9 Mar 2021

Cite this