Akın Kazakçıand Mehdi Cherti
Research Subjects
Research Interests
Akın Kazakçıand Mehdi Cherti has a total of 1 co-authors. Here are the top co-authors by number of shared publications:
- Balázs Kégl
LAL/LRI University of Paris-Sud CNRS 91898 Orsay France
1 shared publication
Latest Publications
- Open Access
Digits that are not: Generating new types through deep neural nets
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 autoencoder. 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.
Open AccessDigits that are not: Generating new types through deep neural nets
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 autoencoder. 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.