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

This paper introduces a novel unsupervised learning paradigm inspired byGerald Edelman's theory of neuronal group selection ("Neural Darwinism"). Thepresented automaton learns to recognize arbitrary symbols (e.g., letters of analphabet) when they are presented repeatedly, as they are when children learnto read. On a second hierarchical level, the model creates abstract categoriesrepresenting the learnt symbols. The fundamental computational unit are simpleMcCulloch-Pitts neurons arranged into fully-connected groups (Hopfield networkswith randomly initialized weights), which are "selected", in an evolutionarysense, through symbol presentation. The learning process is fully tractable andeasily interpretable for humans, in contrast to most neural networkarchitectures. Computational properties of Hopfield networks enabling patternrecognition are discussed. In simulations, the model achieves high accuracy inlearning the letters of the Latin alphabet, presented as binary patterns on agrid. This paper is a proof of concept with no claims to state-of-the-artperformance in letter recognition, but hopefully inspires new thinking inbio-inspired machine learning.

Unsupervised learning architecture based on neural Darwinism and Hopfield networks recognizes symbols with high accuracy