Browsing by Author "Colton, Simon"
Now showing 1 - 3 of 3
- Results Per Page
- Sort Options
- Automating Generative Deep Learning for Artistic Purposes: Challenges and Opportunities
A4 Artikkeli konferenssijulkaisussa(2021-09-01) Berns, Sebastian; Broad, Terence; Guckelsberger, Christian; Colton, SimonWe present a framework for automating generative deep learning with a specific focus on artistic applications. The framework provides opportunities to hand over creative responsibilities to a generative system as targets for automation. For the definition of targets, we adopt core concepts from automated machine learning and an analysis of generative deep learning pipelines, both in standard and artistic settings. To motivate the framework, we argue that automation aligns well with the goal of increasing the creative responsibility of a generative system, a central theme in computational creativity research. We understand automation as the challenge of granting a generative system more creative autonomy, by framing the interaction between the user and the system as a co-creative process. The development of the framework is informed by our analysis of the relationship between automation and creative autonomy. An illustrative example shows how the framework can give inspiration and guidance in the process of handing over creative responsibility. - On the Machine Condition and its Creative Expression
A4 Artikkeli konferenssijulkaisussa(2020-09-15) Colton, Simon; Pease, Alison; Guckelsberger, Christian; McCormack, Jon; Llano, Maria TeresaThe human condition can be characterised as the most essential characteristics, events and situations which describe human existence. We propose that a parallel discussion of the machine condition could improve public understanding of computational systems in general, and advance perception of creativity in computational creativity systems in particular. We present a framework for machines to creatively express their existence, sketch some aspects of the machine condition, and describe potential benefits of this approach. - Towards Mode Balancing of Generative Models via Diversity Weights
A4 Artikkeli konferenssijulkaisussa(2023) Berns, Sebastian; Colton, Simon; Guckelsberger, ChristianLarge data-driven image models are extensively used to support creative and artistic work. Under the currently predominant distribution-fitting paradigm, a dataset is treated as ground truth to be approximated as closely as possible. Yet, many creative applications demand a diverse range of output, and creators often strive to actively diverge from a given data distribution. We argue that an adjustment of modelling objectives, from pure mode coverage towards mode balancing, is necessary to accommodate the goal of higher output diversity. We present diversity weights, a training scheme that increases a model's output diversity by balancing the modes in the training dataset. First experiments in a controlled setting demonstrate the potential of our method. We discuss connections of our approach to diversity, equity, and inclusion in generative machine learning more generally, and computational creativity specifically. An implementation of our algorithm is available at https://github.com/sebastianberns/diversity-weights.