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

Gradient descent algorithm is the most utilized method when optimizingmachine learning issues. However, there exists many local minimums and saddlepoints in the loss function, especially for high dimensional non-convexoptimization problems like deep learning. Gradient descent may make lossfunction trapped in these local intervals which impedes further optimization,resulting in poor generalization ability. This paper proposes the SA-GDalgorithm which introduces the thought of simulated annealing algorithm togradient descent. SA-GD method offers model the ability of mounting hills inprobability, tending to enable the model to jump out of these local areas andconverge to a optimal state finally. We took CNN models as an example andtested the basic CNN models on various benchmark datasets. Compared to thebaseline models with traditional gradient descent algorithm, models with SA-GDalgorithm possess better generalization ability without sacrificing theefficiency and stability of model convergence. In addition, SA-GD can beutilized as an effective ensemble learning approach which improves the finalperformance significantly.

SA-GD: Improved Gradient Descent Learning Strategy with Simulated Annealing