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

Softmax activation is commonly used to output the probability distributionover categories based on certain distance metric. In scenarios like one-shotlearning, the distance metric is often chosen to be squared Euclidean distancebetween the query sample and the category prototype. This practice works wellin most time. However, we find that choosing squared Euclidean distance maycause distance explosion leading gradients to be extremely sparse in the earlystage of back propagation. We term this phenomena as the early sparse gradientsproblem. Though it doesn't deteriorate the convergence of the model, it may setup a barrier to further model improvement. To tackle this problem, we proposeto use leaky squared Euclidean distance to impose a restriction on distances.In this way, we can avoid distance explosion and increase the magnitude ofgradients. Extensive experiments are conducted on Omniglot and miniImageNetdatasets. We show that using leaky squared Euclidean distance can improveone-shot classification accuracy on both datasets.

Tackling Early Sparse Gradients in Softmax Activation Using Leaky Squared Euclidean Distance