Convergence Analysis of Batch Gradient Algorithm for Three Classes of Sigma-Pi Neural Networks

Authors:
Chao Zhang;Wei Wu;Yan Xiong
Affiliations:
Department of Applied Mathematics, Dalian University of Technology, Dalian, P. R. China 116024;Department of Applied Mathematics, Dalian University of Technology, Dalian, P. R. China 116024;Department of Applied Mathematics, Dalian University of Technology, Dalian, P. R. China 116024
Venue:
Neural Processing Letters
Year:
2007

Citing 6
Cited 2

Product units: a computationally powerful and biologically plausible extension to backpropagation networks

Neural Computation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
How to make sigma-pi neural networks perform perfectly on regular training sets

Neural Networks
Neuro-Dynamic Programming

Neuro-Dynamic Programming
Deterministic convergence of an online gradient method for BP neural networks

IEEE Transactions on Neural Networks
A framework for improved training of Sigma-Pi networks

IEEE Transactions on Neural Networks

Convergence of a Batch Gradient Algorithm with Adaptive Momentum for Neural Networks

Neural Processing Letters
Boundedness and convergence of batch back-propagation algorithm with penalty for feedforward neural networks

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Sigma-Pi (Σ-驴) neural networks (SPNNs) are known to provide more powerful mapping capability than traditional feed-forward neural networks. A unified convergence analysis for the batch gradient algorithm for SPNN learning is presented, covering three classes of SPNNs: Σ-驴-Σ, Σ-Σ-驴 and Σ-驴-Σ-驴. The monotonicity of the error function in the iteration is also guaranteed.