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

In this paper, we present a new idea for Transfer Learning (TL) based onGibbs Sampling. Gibbs sampling is an algorithm in which instances are likely totransfer to a new state with a higher possibility with respect to a probabilitydistribution. We find that such an algorithm can be employed to transferinstances between domains. Restricted Boltzmann Machine (RBM) is an energybased model that is very feasible for being trained to represent a datadistribution and also for performing Gibbs sampling. We used RBM to capturedata distribution of the source domain and use it in order to cast targetinstances into new data with a distribution similar to the distribution ofsource data. Using datasets that are commonly used for evaluation of TLmethods, we show that our method can successfully enhance target classificationby a considerable ratio. Additionally, the proposed method has the advantageover common DA methods that it needs no target data during the process oftraining of models.

Between-Domain Instance Transition Via the Process of Gibbs Sampling in RBM