Active Divergence with Generative Deep Learning -- A Survey and Taxonomy

Generative deep learning systems offer powerful tools for artefact generation, given their ability to model distributions of data and generate high-fidelity results. In the context of computational creativity, however, a major shortcoming is that they are unable to explicitly diverge from the training data in creative ways and are limited to fitting the target data distribution. To address these limitations, there have been a growing number of approaches for optimising, hacking and rewriting these models in order to actively diverge from the training data. We present a taxonomy and comprehensive survey of the state of the art of active divergence techniques, highlighting the potential for computational creativity researchers to advance these methods and use deep generative models in truly creative systems.

Guru, Partner, or Pencil Sharpener? Understanding Designers' Attitudes Towards Intelligent Creativity Support Tools

Creativity Support Tools (CST) aim to enhance human creativity, but the deeply personal and subjective nature of creativity makes the design of universal support tools challenging. Individuals develop personal approaches to creativity, particularly in the context of commercial design where signature styles and techniques are valuable commodities. Artificial Intelligence (AI) and Machine Learning (ML) techniques could provide a means of creating 'intelligent' CST which learn and adapt to personal styles of creativity. Identifying what kind of role such tools could play in the design process requires a better understanding of designers' attitudes towards working with AI, and their willingness to include it in their personal creative process. This paper details the results of a survey of professional designers which indicates a positive and pragmatic attitude towards collaborating with AI tools, and a particular opportunity for incorporating them in the research stages of a design project.

Network Bending: Manipulating The Inner Representations of Deep Generative Models

We introduce a new framework for interacting with and manipulating deep generative models that we call network bending. We present a comprehensive set of deterministic transformations that can be inserted as distinct layers into the computational graph of a trained generative neural network and applied during inference. In addition, we present a novel algorithm for clustering features based on their spatial activation maps. This allows features to be grouped together based on spatial similarity in an unsupervised fashion. This results in the meaningful manipulation of sets of features that correspond to the generation of a broad array of semantically significant aspects of the generated images. We demonstrate these transformations on the official pre-trained StyleGAN2 model trained on the FFHQ dataset. In doing so, we lay the groundwork for future interactive multimedia systems where the inner representation of deep generative models are manipulated for greater creative expression, whilst also increasing our understanding of how such "black-box systems" can be more meaningfully interpreted.

Learning to See: You Are What You See

The authors present a visual instrument developed as part of the creation of the artwork Learning to See. The artwork explores bias in artificial neural networks and provides mechanisms for the manipulation of specifically trained for real-world representations. The exploration of these representations acts as a metaphor for the process of developing a visual understanding and/or visual vocabulary of the world. These representations can be explored and manipulated in real time, and have been produced in such a way so as to reflect specific creative perspectives that call into question the relationship between how both artificial neural networks and humans may construct meaning.

Deep Meditations: Controlled navigation of latent space

We introduce a method which allows users to creatively explore and navigate the vast latent spaces of deep generative models. Specifically, our method enables users to \textit{discover} and \textit{design} \textit{trajectories} in these high dimensional spaces, to construct stories, and produce time-based media such as videos---\textit{with meaningful control over narrative}. Our goal is to encourage and aid the use of deep generative models as a medium for creative expression and story telling with meaningful human control. Our method is analogous to traditional video production pipelines in that we use a conventional non-linear video editor with proxy clips, and conform with arrays of latent space vectors. Examples can be seen at \url{http://deepmeditations.ai}.

Amplifying The Uncanny

Deep neural networks have become remarkably good at producing realistic deepfakes, images of people that are (to the untrained eye) indistinguishable from real images. These are produced by algorithms that learn to distinguish between real and fake images and are optimised to generate samples that the system deems realistic. This paper, and the resulting series of artworks Being Foiled explore the aesthetic outcome of inverting this process and instead optimising the system to generate images that it sees as being fake. Maximising the unlikelihood of the data and in turn, amplifying the uncanny nature of these machine hallucinations.

Transforming the output of GANs by fine-tuning them with features from different datasets

In this work we present a method for fine-tuning pre-trained GANs with features from different datasets, resulting in the transformation of the output distribution into a new distribution with novel characteristics. The weights of the generator are updated using the weighted sum of the losses from a cross-dataset classifier and the frozen weights of the pre-trained discriminator. We discuss details of the technical implementation and share some of the visual results from this training process.

Searching for an (un)stable equilibrium: experiments in training generative models without data

This paper details a developing artistic practice around an ongoing series of works called (un)stable equilibrium. These works are the product of using modern machine toolkits to train generative models without data, an approach akin to traditional generative art where dynamical systems are explored intuitively for their latent generative possibilities. We discuss some of the guiding principles that have been learnt in the process of experimentation, present details of the implementation of the first series of works and discuss possibilities for future experimentation.

Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks

We propose a computational framework to learn stylisation patterns from example drawings or writings, and then generate new trajectories that possess similar stylistic qualities. We particularly focus on the generation and stylisation of trajectories that are similar to the ones that can be seen in calligraphy and graffiti art. Our system is able to extract and learn dynamic and visual qualities from a small number of user defined examples which can be recorded with a digitiser device, such as a tablet, mouse or motion capture sensors. Our system is then able to transform new user drawn traces to be kinematically and stylistically similar to the training examples. We implement the system using a Recurrent Mixture Density Network (RMDN) combined with a representation given by the parameters of the Sigma Lognormal model, a physiologically plausible model of movement that has been shown to closely reproduce the velocity and trace of human handwriting gestures.

Real-time interactive sequence generation and control with Recurrent Neural Network ensembles

Recurrent Neural Networks (RNN), particularly Long Short Term Memory (LSTM) RNNs, are a popular and very successful method for learning and generating sequences. However, current generative RNN techniques do not allow real-time interactive control of the sequence generation process, thus aren't well suited for live creative expression. We propose a method of real-time continuous control and 'steering' of sequence generation using an ensemble of RNNs and dynamically altering the mixture weights of the models. We demonstrate the method using character based LSTM networks and a gestural interface allowing users to 'conduct' the generation of text.