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

Training in supervised deep learning is computationally demanding, and theconvergence behavior is usually not fully understood. We introduce and study asecond-order stochastic quasi-Gauss-Newton (SQGN) optimization method thatcombines ideas from stochastic quasi-Newton methods, Gauss-Newton methods, andvariance reduction to address this problem. SQGN provides excellent accuracywithout the need for experimenting with many hyper-parameter configurations,which is often computationally prohibitive given the number of combinations andthe cost of each training process. We discuss the implementation of SQGN withTensorFlow, and we compare its convergence and computational performance toselected first-order methods using the MNIST benchmark and a large-scaleseismic tomography application from Earth science.

Deep Neural Network Learning with Second-Order Optimizers -- a Practical Study with a Stochastic Quasi-Gauss-Newton Method