Digits that are not: Generating new types through deep neural netsReport as inadecuate

Digits that are not: Generating new types through deep neural nets - Download this document for free, or read online. Document in PDF available to download.

1 CGS i3 - Centre de Gestion Scientifique i3 2 LRI - Laboratoire de Recherche en Informatique 3 LAL - Laboratoire de l-Accélérateur Linéaire 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 : 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.

Author: Akın Kazakçı - Cherti Mehdi - Balázs Kégl -

Source: https://hal.archives-ouvertes.fr/


Related documents