English

Toward A Neuro-inspired Creative Decoder

Artificial Intelligence 2020-04-24 v4 Machine Learning Neural and Evolutionary Computing

Abstract

Creativity, a process that generates novel and meaningful ideas, involves increased association between task-positive (control) and task-negative (default) networks in the human brain. Inspired by this seminal finding, in this study we propose a creative decoder within a deep generative framework, which involves direct modulation of the neuronal activation pattern after sampling from the learned latent space. The proposed approach is fully unsupervised and can be used off-the-shelf. Several novelty metrics and human evaluation were used to evaluate the creative capacity of the deep decoder. Our experiments on different image datasets (MNIST, FMNIST, MNIST+FMNIST, WikiArt and CelebA) reveal that atypical co-activation of highly activated and weakly activated neurons in a deep decoder promotes generation of novel and meaningful artifacts.

Keywords

Cite

@article{arxiv.1902.02399,
  title  = {Toward A Neuro-inspired Creative Decoder},
  author = {Payel Das and Brian Quanz and Pin-Yu Chen and Jae-wook Ahn and Dhruv Shah},
  journal= {arXiv preprint arXiv:1902.02399},
  year   = {2020}
}

Comments

Accepted to IJCAI 2020

R2 v1 2026-06-23T07:34:03.859Z