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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

How to reduce the requirement on training dataset size is a hot topic in deeplearning community. One straightforward way is to reuse some pre-trainedparameters. Some previous work like Deep transfer learning reuse the modelparameters trained for the first task as the starting point for the secondtask, and semi-supervised learning is trained upon a combination of labeled andunlabeled data. However, the fundamental reason of the success of these methodsis unclear. In this paper, the reusability of parameters in each layer of adeep convolutional neural network is experimentally quantified by using anetwork to do segmentation and auto-encoder task. This paper proves thatnetwork parameters can be reused for two reasons: first, the network featuresare general; Second, there is little difference between the pre-trainedparameters and the ideal network parameters. Through the use of parameterreplacement and comparison, we demonstrate that reusability is different inBN(Batch Normalization)[7] layer and Convolution layer and some observations:(1)Running mean and running variance plays an important role than Weight andBias in BN layer.(2)The weight and bias can be reused in BN layers.( 3) Thenetwork is very sensitive to the weight of convolutional layer.(4) The bias inConvolution layers are not sensitive, and it can be reused directly.

Using UNet and PSPNet to explore the reusability principle of CNN parameters