Style Transfer Generative Adversarial Networks: Learning to Play Chess DifferentlyDownload PDF

28 Mar 2024 (modified: 16 Mar 2017)ICLR 2017 workshop submissionReaders: Everyone
Abstract: The idea of style transfer has largely only been explored in image-based tasks, which we attribute in part to the specific nature of loss functions used for style transfer. We propose a general formulation of style transfer as an extension of generative adversarial networks, by using a discriminator to regularize a generator with an otherwise separate loss function. We apply our approach to the task of learning to play chess in the style of a specific player, and present empirical evidence for the viability of our approach.
TL;DR: A discriminator network is used to regularize a separate generator network to influence the style with which the generator performs a task.
Keywords: Deep learning
Conflicts: virginia.edu
5 Replies

Loading