papers AI Learner
The Github is limit! Click to go to the new site.

Toward A Neuro-inspired Creative Decoder

2019-02-06
Payel Das, Brian Quanz, Pin-Yu Chen, Jaw-wook Ahn

Abstract

Creativity, a process that generates novel and valuable ideas, involves increased association between task-positive (control) and task-negative (default) networks in brain. Inspired by this seminal finding, in this study we propose a creative decoder that directly modulates the neuronal activation pattern, while sampling from the learned latent space. The proposed approach is fully unsupervised and can be used as off-the-shelf. Our experiments on three different image datasets (MNIST, FMNIST, CELEBA) reveal that the co-activation between task-positive and task-negative neurons during decoding in a deep neural net enables generation of novel artifacts. We further identify sufficient conditions on several novelty metrics towards measuring the creativity of generated samples.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1902.02399

PDF

http://arxiv.org/pdf/1902.02399


Similar Posts

Comments