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

In many cases, the computing resources are limited without the benefit fromGPU, especially in the edge devices of IoT enabled systems. It may not be easyto implement complex AI models in edge devices. The Universal ApproximationTheorem states that a shallow neural network (SNN) can represent any nonlinearfunction. However, how fat is an SNN enough to solve a nonlineardecision-making problem in edge devices? In this paper, we focus on thelearnability and robustness of SNNs, obtained by a greedy tight force heuristicalgorithm (performance driven BP) and a loose force meta-heuristic algorithm (avariant of PSO). Two groups of experiments are conducted to examine thelearnability and the robustness of SNNs with Sigmoid activation,learned/optimised by KPI-PDBPs and KPI-VPSOs, where, KPIs (key performanceindicators: error (ERR), accuracy (ACC) and $F_1$ score) are the objectives,driving the searching process. An incremental approach is applied to examinethe impact of hidden neuron numbers on the performance of SNNs,learned/optimised by KPI-PDBPs and KPI-VPSOs. From the engineering prospective,all sensors are well justified for a specific task. Hence, all sensor readingsshould be strongly correlated to the target. Therefore, the structure of an SNNshould depend on the dimensions of a problem space. The experimental resultsshow that the number of hidden neurons up to the dimension number of a problemspace is enough; the learnability of SNNs, produced by KPI-PDBP, is better thanthat of SNNs, optimized by KPI-VPSO, regarding the performance and learningtime on the training data sets; the robustness of SNNs learned by KPI-PDBPs andKPI-VPSOs depends on the data sets; and comparing with other classic machinelearning models, ACC-PDBPs win for almost all tested data sets.

Learnability and Robustness of Shallow Neural Networks Learned With a Performance-Driven BP and a Variant PSO For Edge Decision-Making