Enhancing threshold neural network via suprathreshold stochastic resonance for pattern classification

DOI10.1016/J.PHYSLETA.2021.127387MaRDI QIDQ2233111zbMATH OpenOpenAlexFDO

Authors L. Duan, Fabing Duan, François Chapeau-Blondeau, Xiao-Jie Liu, Derek Abbott

Publication date 14 October 2021

Published in Physics Letters. A (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.physleta.2021.127387

zbMATH Keywords

backpropagationnoise-smoothed activation functionpattern classificationsuprathreshold stochastic resonancethreshold neural network

Mathematics Subject Classification ID

Quantum theory (81-XX) Statistical mechanics, structure of matter (82-XX)

Cites work

• A pseudo-noise approach to direction finding
• Bayes Risk Reduction of Estimators Using Artificial Observation Noise
• Gradient‐based parameter optimization for systems containing discrete‐valued functions
• Noise Benefits in Combined Nonlinear Bayesian Estimators
• Optimum adaptive array stochastic resonance in noisy grayscale image restoration
• Pattern recognition and machine learning.
• Stochastic Resonance
• Suprathreshold stochastic resonance and signal-to-noise ratio improvement in arrays of comparators
• The stochastic delta rule: faster and more accurate deep learning through adaptive weight noise

Cited in

(3)

• Training threshold neural networks by extreme learning machine and adaptive stochastic resonance
• Echo state network activation function based on bistable stochastic resonance
• Exploring the Bayes-oriented noise injection approach in neural networks

Describes a project that uses

Uses Software

• PRMLT

This page was built for publication: Enhancing threshold neural network via suprathreshold stochastic resonance for pattern classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2233111)