A convolutional recursive modified self organizing map for handwritten digits recognition

DOI10.1016/J.NEUNET.2014.08.001zbMath1325.68209DBLPjournals/nn/MohebiB14OpenAlexW2061825952WikidataQ51043085 ScholiaQ51043085MaRDI QIDQ889329

Ehsan Mohebi, Adil M. Bagirov

Publication date: 6 November 2015

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.neunet.2014.08.001

zbMATH Keywords

vector quantizationconvolutional neural networkself organizing mapsrecursive neural networkSOM initializationSOM topology

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)

Uses Software

• MNIST

Cites Work

• Handwritten character recognition through two-stage foreground sub-sampling
• Iterative shrinking method for clustering problems
• Robust path-based spectral clustering
• Large-scale data exploration with the hierarchically growing hyperbolic SOM
• On the equivalence between kernel self-organising maps and self-organising mixture density networks
• Learning multiple linear manifolds with self-organizing networks
• Self-organizing maps.

This page was built for publication: A convolutional recursive modified self organizing map for handwritten digits recognition