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 establish a margin based data dependent generalization error bound for ageneral family of deep neural networks in terms of the depth and width, as wellas the Jacobian of the networks. Through introducing a new characterization ofthe Lipschitz properties of neural network family, we achieve significantlytighter generalization bounds than existing results. Moreover, we show that thegeneralization bound can be further improved for bounded losses. Aside from thegeneral feedforward deep neural networks, our results can be applied to derivenew bounds for popular architectures, including convolutional neural networks(CNNs) and residual networks (ResNets). When achieving same generalizationerrors with previous arts, our bounds allow for the choice of larger parameterspaces of weight matrices, inducing potentially stronger expressive ability forneural networks. Numerical evaluation is also provided to support our theory.

On Tighter Generalization Bound for Deep Neural Networks: CNNs, ResNets, and Beyond