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

This study presents a neural network which uses filters based on logisticmapping (LogNNet). LogNNet has a feedforward network structure, but possessesthe properties of reservoir neural networks. The input weight matrix, set by arecurrent logistic mapping, forms the kernels that transform the input space tothe higher-dimensional feature space. The most effective recognition of ahandwritten digit from MNIST-10 occurs under chaotic behavior of the logisticmap. The correlation of classification accuracy with the value of the Lyapunovexponent was obtained. An advantage of LogNNet implementation on IoT devices isthe significant savings in memory used. At the same time, LogNNet has a simplealgorithm and performance indicators comparable to those of the bestresource-efficient algorithms available at the moment. The presented networkarchitecture uses an array of weights with a total memory size from 1 to 29 kBand achieves a classification accuracy of 80.3-96.3%. Memory is saved due tothe processor, which sequentially calculates the required weight coefficientsduring the network operation using the analytical equation of the logisticmapping. The proposed neural network can be used in implementations ofartificial intelligence based on constrained devices with limited memory, whichare integral blocks for creating ambient intelligence in modern IoTenvironments. From a research perspective, LogNNet can contribute to theunderstanding of the fundamental issues of the influence of chaos on thebehavior of reservoir-type neural networks.

Neural Network for Low-Memory IoT Devices and MNIST Image Recognition Using Kernels Based on Logistic Map