Seeking the Building Blocks of Visual Imagery and Creativity in a Cognitively Inspired Neural Network

TL;DR

This paper investigates how simple, cognitively inspired neural networks can model visual imagery and creativity, demonstrating basic generative capabilities and discussing how memory mechanisms could enhance creative combination generation.

Contribution

It introduces a simplified neural model inspired by cognitive mechanisms that can generate visual shape and color combinations, highlighting potential paths to incorporate creativity.

Findings

Standard neural architecture can generate shape/color combinations from symbolic input.

Generating novel combinations not seen during training remains challenging.

Memory integration could enable the creation of new, unseen combinations.

Abstract

How do we imagine visual objects and combine them to create new forms? To answer this question, we need to explore the cognitive, computational and neural mechanisms underlying imagery and creativity. The body of research on deep learning models with creative behaviors is growing. However, in this paper we suggest that the complexity of such models and their training sets is an impediment to using them as tools to understand human aspects of creativity. We propose using simpler models, inspired by neural and cognitive mechanisms, that are trained with smaller data sets. We show that a standard deep learning architecture can demonstrate imagery by generating shape/color combinations using only symbolic codes as input. However, generating a new combination that was not experienced by the model was not possible. We discuss the limitations of such models, and explain how creativity could be embedded by incorporating memory mechanisms to combine the output of the network into new combinations and use that as new training data.