Out-of-class novelty generation: an experimental foundation * - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Out-of-class novelty generation: an experimental foundation *

Résumé

Constructive machine learning aims at finding one or more instances of a domain which will exhibit some desired properties. Such a process bears a strong similarity with a design process where the ultimate objective is the generation of previously unknown and novel objects by using knowledge about known objects. The aim of the present work is to bring ideas from design theory to machine learning and elaborate an experimental procedure allowing the study of design through machine learning approaches. To this end, we propose an actionable definition of creativity as the generation of out-of-distribution novelty. We assess several metrics designed for evaluating the quality of generative models on this new task. Through extensive experiments on various types of generative models, we find architectures and hyperparameter combinations which lead to out-of-distribution novelty. Such generators can then be used to search a semantically richer and broader space than standard generative models would allow.
Fichier principal
Vignette du fichier
class-novelty-generation (18).pdf (355.56 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01427570 , version 1 (05-01-2017)

Identifiants

  • HAL Id : hal-01427570 , version 1

Citer

Mehdi Cherti, Balázs Kégl, Akin Osman Kazakçi. Out-of-class novelty generation: an experimental foundation *. NIPS 2016 - Neural Information Processing Systems, Dec 2016, Barcelona, Spain. ⟨hal-01427570⟩
676 Consultations
284 Téléchargements

Partager

Gmail Facebook X LinkedIn More