Algorithms that get old : the case of generative deep neural networks. (arXiv:2202.03008v2 [stat.ML] UPDATED)

Web: http://arxiv.org/abs/2202.03008

Generative deep neural networks used in machine learning, like the
Variational Auto-Encoders (VAE), and Generative Adversarial Networks (GANs)
produce new objects each time when asked to do so with the constraint that the
new objects remain similar to some list of examples given as input. However,
this behavior is unlike that of human artists that change their style as times
go by and seldom return to the initial creations. We investigate a situation
where VAEs are used to sample from …

algorithms arxiv deep ml networks neural neural networks