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

Two things seem to be indisputable in the contemporary deep learningdiscourse: 1. The categorical cross-entropy loss after softmax activation isthe method of choice for classification. 2. Training a CNN classifier fromscratch on small datasets does not work well. In contrast to this, we show thatthe cosine loss function provides significantly better performance thancross-entropy on datasets with only a handful of samples per class. Forexample, the accuracy achieved on the CUB-200-2011 dataset without pre-trainingis by 30% higher than with the cross-entropy loss. Further experiments on otherpopular datasets confirm our findings. Moreover, we demonstrate thatintegrating prior knowledge in the form of class hierarchies is straightforwardwith the cosine loss and improves classification performance further.

Deep Learning on Small Datasets without Pre-Training using Cosine Loss