Robust sequential learning of feedforward neural networks in the presence of heavy-tailed noise

DOI10.1016/J.NEUNET.2014.11.001MaRDI QIDQ889372zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Najdan Vuković, Zoran Miljković

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.2014.11.001

zbMATH Keywords

heavy-tailed noisefeedforward neural networksinverse Wishart distributionsequential learningrobust extended Kalman filterstructured variational approximation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• scientific article; zbMATH DE number 1784956
• Robust control methods for on-line statistical learning.
• A probabilistic learning algorithm for robust modeling using neural networks with random weights
• Diffusion learning algorithms for feedforward neural networks
• Robust adaptive learning of feedforward neural networks via LMI optimizations

Cites work

• scientific article; zbMATH DE number 3426675 (Why is no real title available?)
• Title not available (Why is no real title available?)
• A growing and pruning sequential learning algorithm of hyper basis function neural network for function approximation
• A survey of outlier detection methodologies
• Analysis of robust stochastic approximation algorithms for process identification
• Approximate Inference in State-Space Models With Heavy-Tailed Noise
• Generalized multiscale radial basis function networks
• High Breakdown-Point Estimates of Regression by Means of the Minimization of an Efficient Scale
• Novelty detection: a review. I. Statistical approaches
• Novelty detection: a review. II. Neural network based approaches
• Pattern recognition and machine learning.
• Recursive Noise Adaptive Kalman Filtering by Variational Bayesian Approximations
• Regularization algorithms for learning that are equivalent to multilayer networks
• Robust Bayesian clustering
• Robust Estimation in Non-Linear State-Space Models With State-Dependent Noise
• Robust estimation with unknown noise statistics
• Robust full Bayesian learning for radial basis networks
• Robust recursive estimation in the presence of heavy-tailed observation noise
• Sequential Bayesian kernel modelling with non-Gaussian noise
• Sequential Monte Carlo Methods in Practice
• Training radial basis neural networks with the extended Kalman filter

Cited in

(2)

• Robust manifold broad learning system for large-scale noisy chaotic time series prediction: a perturbation perspective
• A stochastic variational framework for recurrent Gaussian processes models

Describes a project that uses

Uses Software

• PRMLT
• UCI

This page was built for publication: Robust sequential learning of feedforward neural networks in the presence of heavy-tailed noise

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q889372)