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

Machine Learning has been applied in a wide range of tasks throughout thelast years, ranging from image classification to autonomous driving and naturallanguage processing. Restricted Boltzmann Machine (RBM) has received recentattention and relies on an energy-based structure to model data probabilitydistributions. Notwithstanding, such a technique is susceptible to adversarialmanipulation, i.e., slightly or profoundly modified data. An alternative toovercome the adversarial problem lies in the Generative Adversarial Networks(GAN), capable of modeling data distributions and generating adversarial datathat resemble the original ones. Therefore, this work proposes to artificiallygenerate RBMs using Adversarial Learning, where pre-trained weight matricesserve as the GAN inputs. Furthermore, it proposes to sample copious amounts ofmatrices and combine them into ensembles, alleviating the burden of trainingnew models'. Experimental results demonstrate the suitability of the proposedapproach under image reconstruction and image classification tasks, anddescribe how artificial-based ensembles are alternatives to pre-training vastamounts of RBMs.

Fast Ensemble Learning Using Adversarially-Generated Restricted Boltzmann Machines