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

In radial basis function neural network (RBFNN) based real-time learningtasks, forgetting mechanisms are widely used such that the neural network cankeep its sensitivity to new data. However, with forgetting mechanisms, someuseful knowledge will get lost simply because they are learned a long time ago,which we refer to as the passive knowledge forgetting phenomenon. To addressthis problem, this paper proposes a real-time training method named selectivememory recursive least squares (SMRLS) in which the classical forgettingmechanisms are recast into a memory mechanism. Different from the forgettingmechanism, which mainly evaluates the importance of samples according to thetime when samples are collected, the memory mechanism evaluates the importanceof samples through both temporal and spatial distribution of samples. WithSMRLS, the input space of the RBFNN is evenly divided into a finite number ofpartitions and a synthesized objective function is developed using synthesizedsamples from each partition. In addition to the current approximation error,the neural network also updates its weights according to the recorded data fromthe partition being visited. Compared with classical training methods includingthe forgetting factor recursive least squares (FFRLS) and stochastic gradientdescent (SGD) methods, SMRLS achieves improved learning speed andgeneralization capability, which are demonstrated by corresponding simulationresults.

Selective Memory Recursive Least Squares: Recast Forgetting into Memory in RBF Neural Network Based Real-Time Learning