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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Activation function is a key component in deep learning that performsnon-linear mappings between the inputs and outputs. Rectified Linear Unit(ReLU) has been the most popular activation function across the deep learningcommunity. However, ReLU contains several shortcomings that can result ininefficient training of the deep neural networks, these are: 1) the negativecancellation property of ReLU tends to treat negative inputs as unimportantinformation for the learning, resulting in a performance degradation; 2) theinherent predefined nature of ReLU is unlikely to promote additionalflexibility, expressivity, and robustness to the networks; 3) the meanactivation of ReLU is highly positive and leads to bias shift effect in networklayers; and 4) the multilinear structure of ReLU restricts the non-linearapproximation power of the networks. To tackle these shortcomings, this paperintroduced Parametric Flatten-T Swish (PFTS) as an alternative to ReLU. Bytaking ReLU as a baseline method, the experiments showed that PFTS improvedclassification accuracy on SVHN dataset by 0.31%, 0.98%, 2.16%, 17.72%, 1.35%,0.97%, 39.99%, and 71.83% on DNN-3A, DNN-3B, DNN-4, DNN- 5A, DNN-5B, DNN-5C,DNN-6, and DNN-7, respectively. Besides, PFTS also achieved the highest meanrank among the comparison methods. The proposed PFTS manifested highernon-linear approximation power during training and thereby improved thepredictive performance of the networks.

Parametric Flatten-T Swish: An Adaptive Non-linear Activation Function For Deep Learning