An efficient initialization mechanism of neurons for winner takes all neural network implemented in the CMOS technology

DOI10.1016/J.AMC.2015.04.123zbMath1410.92013OpenAlexW838382172MaRDI QIDQ669659

Marta Kolasa, Rafał Długosz, Pierre-André Farine, Tomasz Talaśka

Publication date: 15 March 2019

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

Full work available at URL: https://doi.org/10.1016/j.amc.2015.04.123

zbMATH Keywords

analog circuitsCMOS implementationconvex combination methodinitialization mechanismlow energy consumptionwinner takes all neural network

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20)

Related Items (2)

Efficient methods of initializing neuron weights in self-organizing networks implemented in hardware ⋮ A novel, flexible circuit used to implement selected mathematical operations for AI algorithms optimized for hardware applications

Cites Work

• Principles of Artificial Neural Networks
• Self-organizing maps.
• Unnamed Item

This page was built for publication: An efficient initialization mechanism of neurons for winner takes all neural network implemented in the CMOS technology