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 examine the effect of the Group Lasso (gLasso) regularizer in selectingthe salient nodes of Deep Neural Network (DNN) hidden layers by applying aDNN-HMM hybrid speech recognizer to TED Talks speech data. We test two types ofgLasso regularization, one for outgoing weight vectors and another for incomingweight vectors, as well as two sizes of DNNs: 2048 hidden layer nodes and 4096nodes. Furthermore, we compare gLasso and L2 regularizers. Our experimentresults demonstrate that our DNN training, in which the gLasso regularizer wasembedded, successfully selected the hidden layer nodes that are necessary andsufficient for achieving high classification power.

Automatic Node Selection for Deep Neural Networks using Group Lasso Regularization