Batch gradient method with smoothing L₁/2 regularization for training of feedforward neural networks

DOI10.1016/J.NEUNET.2013.11.006MaRDI QIDQ470178zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Wei Wu, Qinwei Fan, Jacek M. Zurada, Dakun Yang, Jian Wang, Yan Liu

Publication date 12 November 2014

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2013.11.006

zbMATH Keywords

convergencefeedforward neural networksbatch gradient methodsmoothing \(L_{1/2}\) regularization

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)

Recommendations

• \(L_{1/2}\) regularization methods for weights sparsification of neural networks
• Convergence analyses on sparse feedforward neural networks via group lasso regularization
• Make _1 regularization effective in training sparse CNN
• A Penalty-Function Approach for Pruning Feedforward Neural Networks
• The convergence analysis of spikeprop algorithm with smoothing \(L_{1/2}\) regularization

Cites work

• scientific article; zbMATH DE number 51537 (Why is no real title available?)
• scientific article; zbMATH DE number 3444596 (Why is no real title available?)
• scientific article; zbMATH DE number 1916734 (Why is no real title available?)
• A Penalty-Function Approach for Pruning Feedforward Neural Networks
• A modified gradient-based neuro-fuzzy learning algorithm and its convergence
• A one-layer recurrent neural network for constrained pseudoconvex optimization and its application for dynamic portfolio optimization
• Competitive Layer Model of Discrete-Time Recurrent Neural Networks with LT Neurons
• Convergence analysis of three classes of Split-complex gradient algorithms for complex-valued recurrent neural networks
• Estimating the dimension of a model
• Generalized Neural Network for Nonsmooth Nonlinear Programming Problems
• Global Convergence Rate of Recurrently Connected Neural Networks
• Improve robustness of sparse PCA by \(L_{1}\)-norm maximization
• Minimization algorithms based on supervisor and searcher cooperation
• Neural networks in optimization
• Some Comments on C P
• Sparse SAR imaging based on \(L_{1/2}\) regularization

Cited in

(10)

• A New Smoothing Approach for Piecewise Smooth Functions: Application to Some Fundamental Functions
• Convergence analyses on sparse feedforward neural networks via group lasso regularization
• Convergence analysis for sigma-pi-sigma neural network based on some relaxed conditions
• Deterministic convergence analysis via smoothing group Lasso regularization and adaptive momentum for Sigma-Pi-Sigma neural network
• Convergence analysis of an augmented algorithm for fully complex-valued neural networks
• Convergence analysis of the batch gradient-based neuro-fuzzy learning algorithm with smoothing \(L_{1/2}\) regularization for the first-order Takagi-Sugeno system
• \(L_{1/2}\) regularization methods for weights sparsification of neural networks
• A backpropagation learning algorithm with graph regularization for feedforward neural networks
• The convergence analysis of spikeprop algorithm with smoothing \(L_{1/2}\) regularization
• Modeling of complex dynamic systems using differential neural networks with the incorporation of a priori knowledge

This page was built for publication: Batch gradient method with smoothing \(L_{1/2}\) regularization for training of feedforward neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q470178)