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

Binarization of neural network models is considered as one of the promisingmethods to deploy deep neural network models on resource-constrainedenvironments such as mobile devices. However, Binary Neural Networks (BNNs)tend to suffer from severe accuracy degradation compared to the full-precisioncounterpart model. Several techniques were proposed to improve the accuracy ofBNNs. One of the approaches is to balance the distribution of binaryactivations so that the amount of information in the binary activations becomesmaximum. Based on extensive analysis, in stark contrast to previous work, weargue that unbalanced activation distribution can actually improve the accuracyof BNNs. We also show that adjusting the threshold values of binary activationfunctions results in the unbalanced distribution of the binary activation,which increases the accuracy of BNN models. Experimental results show that theaccuracy of previous BNN models (e.g. XNOR-Net and Bi-Real-Net) can be improvedby simply shifting the threshold values of binary activation functions withoutrequiring any other modification.

Improving Accuracy of Binary Neural Networks using Unbalanced Activation Distribution