Active Divergence with Generative Deep Learning - A Survey and Taxonomy
Active Divergence with Generative Deep Learning - A Survey and Taxonomy
复制标题
DOI：
--
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
Terence Broad;Sebastian Berns;S. Colton;M. Grierson
中科院分区：
文献类型：
--
作者：
Terence Broad;Sebastian Berns;S. Colton;M. Grierson
生成式深度学习系统为人工制品生成提供了强大的工具，因为它们能够对数据分布进行建模并生成高保真结果。然而，在计算创造力的背景下，一个主要缺点是它们无法以创造性的方式明确地偏离训练数据，并且仅限于拟合目标数据分布。为了解决这些限制，已经有越来越多的方法来优化、破解和重写这些模型，以主动偏离训练数据。我们对主动发散技术的最新技术进行了分类和全面调查，强调了计算创造力研究人员推进这些方法并在真正的创造性系统中使用深度生成模型的潜力。
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.