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

Artificial neural networks (ANNs), inspired by the interconnection of realneurons, have achieved unprecedented success in various fields such as computervision and natural language processing. Recently, a novel mathematical ANNmodel, known as the dendritic neuron model (DNM), has been proposed to addressnonlinear problems by more accurately reflecting the structure of real neurons.However, the single-output design limits its capability to handle multi-outputtasks, significantly lowering its applications. In this paper, we propose anovel multi-in and multi-out dendritic neuron model (MODN) to tacklemulti-output tasks. Our core idea is to introduce a filtering matrix to thesoma layer to adaptively select the desired dendrites to regress each output.Because such a matrix is designed to be learnable, MODN can explore therelationship between each dendrite and output to provide a better solution todownstream tasks. We also model a telodendron layer into MODN to simulatebetter the real neuron behavior. Importantly, MODN is a more general andunified framework that can be naturally specialized as the DNM by customizingthe filtering matrix. To explore the optimization of MODN, we investigate bothheuristic and gradient-based optimizers and introduce a 2-step training methodfor MODN. Extensive experimental results performed on 11 datasets on bothbinary and multi-class classification tasks demonstrate the effectiveness ofMODN, with respect to accuracy, convergence, and generality.

A Multi-In and Multi-Out Dendritic Neuron Model and its Optimization