Training threshold neural networks by extreme learning machine and adaptive stochastic resonance

DOI10.1016/J.PHYSLETA.2022.128008MaRDI QIDQ2079079OpenAlexWikidataFDO

Authors Zejia Chen, Fabing Duan, François Chapeau-Blondeau, Derek Abbott

Publication date 4 March 2022

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

Full work available at URL https://doi.org/10.1016/j.physleta.2022.128008

zbMATH Keywords

classificationextreme learning machinefunction approximationnoise injectionadaptive stochastic resonancethreshold network

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Artificial neural networks and deep learning (68T07)

Recommendations

• Training neural networks with structured noise improves classification and generalization
• Evolutionary extreme learning machine
• scientific article; zbMATH DE number 1728476
• Advances in Neural Networks – ISNN 2005
• Training an extreme learning machine by localized generalization error model

Cites work

• A logical calculus of the ideas immanent in nervous activity
• A novel stochastic resonance model based on bistable stochastic pooling network and its application
• Bayes Risk Reduction of Estimators Using Artificial Observation Noise
• Echo state network activation function based on bistable stochastic resonance
• Emergence of stochastic resonance in a two-compartment hippocampal pyramidal neuron model
• Enhancing threshold neural network via suprathreshold stochastic resonance for pattern classification
• Gradient‐based parameter optimization for systems containing discrete‐valued functions
• MMSE Approximation For Sparse Coding Algorithms Using Stochastic Resonance
• Nonparametric One-Bit Quantizers for Distributed Estimation
• Self-induced stochastic resonance in an excitable potential well
• Stochastic Resonance
• Stochastic resonance in hybrid scale-free neuronal networks
• 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

Describes a project that uses

Uses Software

• UCI
• XNOR-Net

This page was built for publication: Training threshold neural networks by extreme learning machine and adaptive stochastic resonance

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2079079)