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

Current deep learning architectures show remarkable performance when trainedin large-scale, controlled datasets. However, the predictive ability of thesearchitectures significantly decreases when learning new classes incrementally.This is due to their inclination to forget the knowledge acquired frompreviously seen data, a phenomenon termed catastrophic-forgetting. On the otherhand, Self-Organizing Maps (SOMs) can model the input space utilizingconstrained k-means and thus maintain past knowledge. Here, we propose a novelalgorithm inspired by biological neurons, termed Dendritic-Self-Organizing Map(DendSOM). DendSOM consists of a single layer of SOMs, which extract patternsfrom specific regions of the input space accompanied by a set of hit matrices,one per SOM, which estimate the association between units and labels. Thebest-matching unit of an input pattern is selected using the maximum cosinesimilarity rule, while the point-wise mutual information is employed for classinference. DendSOM performs unsupervised feature extraction as it does not uselabels for targeted updating of the weights. It outperforms classical SOMs andseveral state-of-the-art continual learning algorithms on benchmark datasets,such as the Split-MNIST and Split-CIFAR-10. We propose that the incorporationof neuronal properties in SOMs may help remedy catastrophic forgetting.

Dendritic Self-Organizing Maps for Continual Learning