Skip to Main content Skip to Navigation

Deep generative neural networks for novelty generation : a foundational framework, metrics and experiments

Abstract : In recent years, significant advances made in deep neural networks enabled the creation of groundbreaking technologies such as self-driving cars and voice-enabled personal assistants. Almost all successes of deep neural networks are about prediction, whereas the initial breakthroughs came from generative models. Today, although we have very powerful deep generative modeling techniques, these techniques are essentially being used for prediction or for generating known objects (i.e., good quality images of known classes): any generated object that is a priori unknown is considered as a failure mode (Salimans et al., 2016) or as spurious (Bengio et al., 2013b). In other words, when prediction seems to be the only possible objective, novelty is seen as an error that researchers have been trying hard to eliminate. This thesis defends the point of view that, instead of trying to eliminate these novelties, we should study them and the generative potential of deep nets to create useful novelty, especially given the economic and societal importance of creating new objects in contemporary societies. The thesis sets out to study novelty generation in relationship with data-driven knowledge models produced by deep generative neural networks. Our first key contribution is the clarification of the importance of representations and their impact on the kind of novelties that can be generated: a key consequence is that a creative agent might need to rerepresent known objects to access various kinds of novelty. We then demonstrate that traditional objective functions of statistical learning theory, such as maximum likelihood, are not necessarily the best theoretical framework for studying novelty generation. We propose several other alternatives at the conceptual level. A second key result is the confirmation that current models, with traditional objective functions, can indeed generate unknown objects. This also shows that even though objectives like maximum likelihood are designed to eliminate novelty, practical implementations do generate novelty. Through a series of experiments, we study the behavior of these models and the novelty they generate. In particular, we propose a new task setup and metrics for selecting good generative models. Finally, the thesis concludes with a series of experiments clarifying the characteristics of models that can exhibit novelty. Experiments show that sparsity, noise level, and restricting the capacity of the net eliminates novelty and that models that are better at recognizing novelty are also good at generating novelty.
Complete list of metadatas

Cited literature [255 references]  Display  Hide  Download
Contributor : Abes Star :  Contact
Submitted on : Friday, July 13, 2018 - 11:18:58 AM
Last modification on : Wednesday, October 14, 2020 - 4:00:14 AM
Long-term archiving on: : Monday, October 15, 2018 - 6:01:48 PM


Version validated by the jury (STAR)


  • HAL Id : tel-01838272, version 1



Mehdi Cherti. Deep generative neural networks for novelty generation : a foundational framework, metrics and experiments. Artificial Intelligence [cs.AI]. Université Paris-Saclay, 2018. English. ⟨NNT : 2018SACLS029⟩. ⟨tel-01838272⟩



Record views


Files downloads