Mechanisms of Artistic Creativity in Deep Learning Neural Networks

TL;DR

This paper explores how deep learning neural networks exhibit creative behaviors through mechanisms that emerge from their core architectures, revealing insights into machine creativity beyond anthropomorphic illusions.

Contribution

It identifies five behavioral characteristics of creativity in DNNs and explains the mechanisms behind their emergence from non-creative training objectives.

Findings

Five creative behaviors are linked to specific mechanisms in DNNs.

These mechanisms originate from architectures designed for classification tasks.

Understanding these mechanisms demystifies machine creativity.

Abstract

The generative capabilities of deep learning neural networks (DNNs) have been attracting increasing attention for both the remarkable artifacts they produce, but also because of the vast conceptual difference between how they are programmed and what they do. DNNs are 'black boxes' where high-level behavior is not explicitly programmed, but emerges from the complex interactions of thousands or millions of simple computational elements. Their behavior is often described in anthropomorphic terms that can be misleading, seem magical, or stoke fears of an imminent singularity in which machines become 'more' than human. In this paper, we examine 5 distinct behavioral characteristics associated with creativity, and provide an example of a mechanisms from generative deep learning architectures that give rise to each these characteristics. All 5 emerge from machinery built for purposes other than the creative characteristics they exhibit, mostly classification. These mechanisms of creative generative capabilities thus demonstrate a deep kinship to computational perceptual processes. By understanding how these different behaviors arise, we hope to on one hand take the magic out of anthropomorphic descriptions, but on the other, to build a deeper appreciation of machinic forms of creativity on their own terms that will allow us to nurture their further development.