# Toward A Neuro-inspired Creative Decoder

## TL;DR

This paper introduces a neuro-inspired creative decoder for deep generative models that enhances the generation of novel and meaningful images by modulating neuronal activation patterns, inspired by brain networks involved in creativity.

## Contribution

A novel unsupervised creative decoder that modulates neuronal activation post-sampling to improve novelty and meaningfulness in generated images.

## Key findings

- Atypical co-activation promotes novelty in generated images.
- The method outperforms baseline models on multiple datasets.
- Human evaluations confirm increased creativity.

## 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.