Skip to Main content Skip to Navigation
Conference papers

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

Akın Kazakçı 1 Cherti Mehdi 2 Balázs Kégl 3, 2, 4
4 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
Abstract : 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.
Document type :
Conference papers
Complete list of metadata

Cited literature [35 references]  Display  Hide  Download
Contributor : Akin Osman Kazakci <>
Submitted on : Thursday, January 5, 2017 - 6:10:05 PM
Last modification on : Friday, April 30, 2021 - 9:55:00 AM
Long-term archiving on: : Thursday, April 6, 2017 - 2:47:26 PM


digits (17) (1).pdf
Files produced by the author(s)


  • HAL Id : hal-01427556, version 1


Akın Kazakçı, 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⟩



Record views


Files downloads