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

Deep CCA is a recently proposed deep neural network extension to thetraditional canonical correlation analysis (CCA), and has been successful formulti-view representation learning in several domains. However, stochasticoptimization of the deep CCA objective is not straightforward, because it doesnot decouple over training examples. Previous optimizers for deep CCA areeither batch-based algorithms or stochastic optimization using largeminibatches, which can have high memory consumption. In this paper, we tacklethe problem of stochastic optimization for deep CCA with small minibatches,based on an iterative solution to the CCA objective, and show that we canachieve as good performance as previous optimizers and thus alleviate thememory requirement.

Stochastic Optimization for Deep CCA via Nonlinear Orthogonal Iterations