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

Mehdi Cherti 1 Balázs Kégl 2, 3, 4 Akın Kazakçı 5
4 TAO - Machine Learning and Optimisation
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : 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.
Type de document :
Communication dans un congrès
Neural Information Processing Systems, Dec 2016, Barcelona, Spain
Liste complète des métadonnées

Littérature citée [19 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01427570
Contributeur : Akin Osman Kazakci <>
Soumis le : jeudi 5 janvier 2017 - 18:20:29
Dernière modification le : jeudi 7 février 2019 - 14:23:23
Document(s) archivé(s) le : jeudi 6 avril 2017 - 14:49:23

Fichier

class-novelty-generation (18)....
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01427570, version 1

Citation

Mehdi Cherti, Balázs Kégl, Akın Kazakçı. Out-of-class novelty generation: an experimental foundation *. Neural Information Processing Systems, Dec 2016, Barcelona, Spain. 〈hal-01427570〉

Partager

Métriques

Consultations de la notice

696

Téléchargements de fichiers

236