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

Stabilizing the complexity of Feedforward Neural Networks (FNNs) for thegiven approximation task can be managed by defining an appropriate modelmagnitude which is also greatly correlated with the generalization quality andcomputational efficiency. However, deciding on the right level of modelcomplexity can be highly challenging in FNN applications. In this paper, a newModel Selection algorithm using Binary Ant Colony Optimization (MS-BACO) isproposed in order to achieve the optimal FNN model in terms of neuralcomplexity and cross-entropy error. MS-BACO is a meta-heuristic algorithm thattreats the problem as a combinatorial optimization problem. By quantifying boththe amount of correlation exists among hidden neurons and the sensitivity ofthe FNN output to the hidden neurons using a sample-based sensitivity analysismethod called, extended Fourier amplitude sensitivity test, the algorithmmostly tends to select the FNN model containing hidden neurons with mostdistinct hyperplanes and high contribution percentage. Performance of theproposed algorithm with three different designs of heuristic information isinvestigated. Comparison of the findings verifies that the newly introducedalgorithm is able to provide more compact and accurate FNN model.

MS-BACO: A new Model Selection algorithm using Binary Ant Colony Optimization for neural complexity and error reduction