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 computationally efficient, stochastic graph-regularizationtechnique that can be utilized for the semi-supervised training of deep neuralnetworks in a parallel or distributed setting. We utilize a technique, firstdescribed in [13] for the construction of mini-batches for stochastic gradientdescent (SGD) based on synthesized partitions of an affinity graph that areconsistent with the graph structure, but also preserve enough stochasticity forconvergence of SGD to good local minima. We show how our technique allows agraph-based semi-supervised loss function to be decomposed into a sum overobjectives, facilitating data parallelism for scalable training of machinelearning models. Empirical results indicate that our method significantlyimproves classification accuracy compared to the fully-supervised case when thefraction of labeled data is low, and in the parallel case, achieves significantspeed-up in terms of wall-clock time to convergence. We show the results forboth sequential and distributed-memory semi-supervised DNN training on a speechcorpus.

Efficient Distributed Semi-Supervised Learning using Stochastic Regularization over Affinity Graphs