Are Deep Neural Networks Creative? v2

[This article is a revised version reposted with permission from KDnuggets]

Are deep neural networks creative? Given recent press coverage of art-generating deep learning, it might seem like a reasonable question. In February, Wired wrote of a gallery exhibition featuring works generated by neural networks. The works were created using Google’s inceptionism, technique that transforms images by iteratively modifying them to enhance the activation of specific neurons in a deep net. Many of the images appear trippy, with rocks transforming into buildings or leaves into insects. Several other researchers have proposed techniques for generating images from neural networks for their aesthetic or stylistic qualities. One method, introduced by Leon Gatys of the University of Tubingen in Germany, can extract the style from one image (say a painting by Van Gogh), and apply it to the content of another image (say a photograph).

In the academic sphere, work on generative image modeling has emerged as a hot research topic. Generative adversarial networks (GANs), introduced by Ian Goodfellow, synthesize novel images by modeling the distribution of seen images. Already some researchers have looked into ways of using GANS to perturb natural images, as by adding smiles to photos.

computer-deep-learning-algorithm-painting-masters-fb__700

In parallel, researchers have also made rapid progress on generative language modeling. Character-level recurrent neural network (RNN) language models now permeate the internet, appearing to hallucinate passages of Shakespeare, Linux source code, and even Donald Trump’s Twitter eruptions. Not surprisingly, a wave of papers and demos soon followed, using LSTMs for generating rap lyrics and poetry.

Clearly, these advances emanate from interesting research and deserve the fascination they inspire.

In this post, rather than address the quality of the work (which is admirable), or explain the methods (which has been done ad nauseam), we’ll instead address the question, can these nets reasonably be called creative? Already, some make the claim. The landing page for deepart.io, a site which commercializes the “Deep Style” work, proclaims “TURN YOUR PHOTOS INTO ART”. If we accept creativity as a prerequisite for art, the claim is made here implicitly.

Continue reading “Are Deep Neural Networks Creative? v2”