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

We describe a graph-based semi-supervised learning framework in the contextof deep neural networks that uses a graph-based entropic regularizer to favorsmooth solutions over a graph induced by the data. The main contribution ofthis work is a computationally efficient, stochastic graph-regularizationtechnique that uses mini-batches that are consistent with the graph structure,but also provides enough stochasticity (in terms of mini-batch data diversity)for convergence of stochastic gradient descent methods to good solutions. Forthis work, we focus on results of frame-level phone classification accuracy onthe TIMIT speech corpus but our method is general and scalable to much largerdata sets. Results indicate that our method significantly improvesclassification accuracy compared to the fully-supervised case when the fractionof labeled data is low, and it is competitive with other methods in the fullylabeled case.

Semi-Supervised Phone Classification using Deep Neural Networks and Stochastic Graph-Based Entropic Regularization