Increasing the Diversity of Deep Generative Models
Keywords:Generative Deep Learning, Creativity, Diversity, PCGML
AbstractGenerative models are used in a variety of applications that require diverse output. Yet, models are primarily optimised for sample fidelity and mode coverage. My work aims to increase the output diversity of generative models for multi-solution tasks. Previously, we analysed the use of generative models in artistic settings and how its objective diverges from distribution fitting. For specific use cases, we quantified the limitations of generative models. Future work will focus on adapting generative modelling for downstream tasks that require a diverse set of high-quality artefacts.
How to Cite
Berns, S. (2022). Increasing the Diversity of Deep Generative Models. Proceedings of the AAAI Conference on Artificial Intelligence, 36(11), 12870-12871. https://doi.org/10.1609/aaai.v36i11.21572
The Twenty - Seventh AAAI / SIGAI Doctoral Consortium