Efficient methods of initializing neuron weights in self-organizing networks implemented in hardware

DOI10.1016/J.AMC.2017.01.043zbMath1427.68276OpenAlexW2587137911MaRDI QIDQ2422884

Rafał Długosz, Tomasz Talaśka, Witold Pedrycz, Marta Kolasa

Publication date: 21 June 2019

Published in: Applied Mathematics and Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.amc.2017.01.043

zbMATH Keywords

self-organizing mapsCMOS implementationinitialization of neuron weightsprogrammable circuits

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Learning and adaptive systems in artificial intelligence (68T05) Hardware implementations of nonnumerical algorithms (VLSI algorithms, etc.) (68W35)

Cites Work

• Unnamed Item
• An efficient initialization mechanism of neurons for winner takes all neural network implemented in the CMOS technology
• A novel recursive algorithm used to model hardware programmable neighborhood mechanism of self-organizing neural networks
• A novel measure for quantifying the topology preservation of self-organizing feature maps
• Principles of Artificial Neural Networks
• Self-organizing maps.

This page was built for publication: Efficient methods of initializing neuron weights in self-organizing networks implemented in hardware