A homomorphic neural network for modeling and prediction

Authors:
Maciej Pedzisz;Danilo P. Mandic
Affiliations:
Imperial College London, Department of Electrical and Electronic Engineering, Communications and Signal Processing Group, London SW7 2AZ, U.K. m.pedziszimperial.ac.uk;Imperial College London, Department of Electrical and Electronic Engineering, Communications and Signal Processing Group, London SW7 2AZ, U.K. d.mandicimperial.ac.uk
Venue:
Neural Computation
Year:
2008

Citing 16
Cited 0

System identification

System identification
On the approximate realization of continuous mappings by neural networks

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

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
Approximation capabilities of multilayer feedforward networks

Neural Networks
Improving the convergence of the back-propagation algorithm

Neural Networks
Towards the Optimal Learning Rate for Backpropagation

Neural Processing Letters
Smaller nets may perform better: special transfer functions

Neural Networks
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Recurrent Neural Networks for Prediction: Learning Algorithms,Architectures and Stability

Recurrent Neural Networks for Prediction: Learning Algorithms,Architectures and Stability
A Data-Reusing Nonlinear Gradient Descent Algorithm for a Class of Complex-Valued Neural Adaptive Filters

Neural Processing Letters
Relationships Between the A Priori and A Posteriori Errors in Nonlinear Adaptive Neural Filters

Neural Computation
The interchangeability of learning rate and gain in backpropagation neural networks

Neural Computation
A stochastic gradient adaptive filter with gradient adaptive stepsize

IEEE Transactions on Signal Processing
Nonlinear adaptive prediction of nonstationary signals

IEEE Transactions on Signal Processing
Fingerprinting protocol for images based on additive homomorphic property

IEEE Transactions on Image Processing
High-order and multilayer perceptron initialization

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

A homomorphic feedforward network (HFFN) for nonlinear adaptive filtering is introduced. This is achieved by a two-layer feedforward architecture with an exponential hidden layer and logarithmic preprocessing step. This way, the overall input-output relationship can be seen as a generalized Volterra model, or as a bank of homomorphic filters. Gradient-based learning for this architecture is introduced, together with some practical issues related to the choice of optimal learning parameters and weight initialization. The performance and convergence speed are verified by analysis and extensive simulations. For rigor, the simulations are conducted on artificial and real-life data, and the performances are compared against those obtained by a sigmoidal feedforward network (FFN) with identical topology. The proposed HFFN proved to be a viable alternative to FFNs, especially in the critical case of online learning on small-and medium-scale data sets.