Toward A Neuro-inspired Creative Decoder
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.
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