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

Backpropagation-based supervised learning has achieved great success incomputer vision tasks. However, its biological plausibility is alwayscontroversial. Recently, the bio-inspired Hebbian learning rule (HLR) hasreceived extensive attention. Self-Organizing Map (SOM) uses the competitiveHLR to establish connections between neurons, obtaining visual features in anunsupervised way. Although the representation of SOM neurons shows somebrain-like characteristics, it is still quite different from the neuronrepresentation in the human visual cortex. This paper proposes an improved SOMwith multi-winner, multi-code, and local receptive field, named mlSOM. Weobserve that the neuron representation of mlSOM is similar to the human visualcortex. Furthermore, mlSOM shows a sparse distributed representation ofobjects, which has also been found in the human inferior temporal area. Inaddition, experiments show that mlSOM achieves better classification accuracythan the original SOM and other state-of-the-art HLR-based methods. The code isaccessible at https://github.com/JiaHongZ/mlSOM.

Extracting the Brain-like Representation by an Improved Self-Organizing Map for Image Classification