Digits that are not: Generating new types through deep neural nets - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Digits that are not: Generating new types through deep neural nets

Résumé

For an artificial creative agent, an essential driver of the search for novelty is a value function which is often provided by the system designer or users. We argue that an important barrier for progress in creativity research is the inability of these systems to develop their own notion of value for novelty. We propose a notion of knowledge-driven creativity that circumvent the need for an externally imposed value function, allowing the system to explore based on what it has learned from a set of referential objects. The concept is illustrated by a specific knowledge model provided by a deep generative au-toencoder. Using the described system, we train a knowledge model on a set of digit images and we use the same model to build coherent sets of new digits that do not belong to known digit types.
Fichier principal
Vignette du fichier
digits (17) (1).pdf (814.04 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01427556 , version 1 (05-01-2017)

Identifiants

  • HAL Id : hal-01427556 , version 1

Citer

Akin Osman Kazakçi, Cherti Mehdi, Balázs Kégl. Digits that are not: Generating new types through deep neural nets. International Conference on Computational Creativity, Jun 2016, Paris, France. ⟨hal-01427556⟩
531 Consultations
286 Téléchargements

Partager

Gmail Facebook X LinkedIn More