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

This work investigates the framework and performance issues of the compositeneural network, which is composed of a collection of pre-trained andnon-instantiated neural network models connected as a rooted directed acyclicgraph for solving complicated applications. A pre-trained neural network modelis generally well trained, targeted to approximate a specific function. Despitea general belief that a composite neural network may perform better than asingle component, the overall performance characteristics are not clear. Inthis work, we construct the framework of a composite network, and prove that acomposite neural network performs better than any of its pre-trained componentswith a high probability bound. In addition, if an extra pre-trained componentis added to a composite network, with high probability, the overall performancewill not be degraded. In the study, we explore a complicated application --PM2.5 prediction -- to illustrate the correctness of the proposed compositenetwork theory. In the empirical evaluations of PM2.5 prediction, theconstructed composite neural network models support the proposed theory andperform better than other machine learning models, demonstrate the advantagesof the proposed framework.

Composite Neural Network: Theory and Application to PM2.5 Prediction