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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

With the vigorous development of artificial intelligence technology, variousengineering technology applications have been implemented one after another.The gradient descent method plays an important role in solving variousoptimization problems, due to its simple structure, good stability and easyimplementation. In multi-node machine learning system, the gradients usuallyneed to be shared. Shared gradients are generally unsafe. Attackers can obtaintraining data simply by knowing the gradient information. In this paper, toprevent gradient leakage while keeping the accuracy of model, we propose thesuper stochastic gradient descent approach to update parameters by concealingthe modulus length of gradient vectors and converting it or them into a unitvector. Furthermore, we analyze the security of super stochastic gradientdescent approach. Our algorithm can defend against attacks on the gradient.Experiment results show that our approach is obviously superior to prevalentgradient descent approaches in terms of accuracy, robustness, and adaptabilityto large-scale batches.

SSGD: A safe and efficient method of gradient descent