Active Divergence with Generative Deep Learning--A Survey and Taxonomy
Generative deep learning systems offer powerful tools for artefact generation, given their
ability to model distributions of data and generate high-fidelity results. In the context of …
ability to model distributions of data and generate high-fidelity results. In the context of …
Explaining artificial intelligence generation and creativity: Human interpretability for novel ideas and artifacts
P Das, LR Varshney - IEEE Signal Processing Magazine, 2022 - ieeexplore.ieee.org
Creativity is often thought of as the pinnacle of human achievement, but artificial intelligence
(AI) is now starting to play a central role in creative processes, whether autonomously or in …
(AI) is now starting to play a central role in creative processes, whether autonomously or in …
Toward a neuro-inspired creative decoder
Creativity, a process that generates novel and meaningful ideas, involves increased
association between task-positive (control) and task-negative (default) networks in the …
association between task-positive (control) and task-negative (default) networks in the …
Challenges in creative generative models for music: a divergence maximization perspective
P Esling - arXiv preprint arXiv:2211.08856, 2022 - arxiv.org
The development of generative Machine Learning (ML) models in creative practices,
enabled by the recent improvements in usability and availability of pre-trained models, is …
enabled by the recent improvements in usability and availability of pre-trained models, is …
[PDF][PDF] ATIAM 2021-ML Project Audio networks hacking: novelty search through active divergence
ACRSP Esling - 2021 - esling.github.io
Variational auto-encoders are generative models whose training is based on two
simultaneous optimization tasks. The first is to build a latent space, that provides a low …
simultaneous optimization tasks. The first is to build a latent space, that provides a low …