English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We present Turbo-Sim, a generalised autoencoder framework derived fromprinciples of information theory that can be used as a generative model. Bymaximising the mutual information between the input and the output of both theencoder and the decoder, we are able to rediscover the loss terms usually foundin adversarial autoencoders and generative adversarial networks, as well asvarious more sophisticated related models. Our generalised framework makesthese models mathematically interpretable and allows for a diversity of newones by setting the weight of each loss term separately. The framework is alsoindependent of the intrinsic architecture of the encoder and the decoder thusleaving a wide choice for the building blocks of the whole network. We applyTurbo-Sim to a collider physics generation problem: the transformation of theproperties of several particles from a theory space, right after the collision,to an observation space, right after the detection in an experiment.

Turbo-Sim: a generalised generative model with a physical latent space