Original Contribution: Optimal filtering algorithms for fast learning in feedforward neural networks

Authors:
Samir Shah;Francesco Palmieri;Michael Datum
Affiliations:
-;-;-
Venue:
Neural Networks
Year:
1992

Citing 3
Cited 24

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Rescaling of variables in back propagation learning

Neural Networks
Adaptive filter theory (2nd ed.)

Adaptive filter theory (2nd ed.)

A New Weight Initialization Method for the MLP with the BP inMulticlass Classification Problems

Neural Processing Letters
Extended Kalman filter-based pruning method for recurrent neural networks

Neural Computation
Incremental Gradient Algorithms with Stepsizes Bounded Away from Zero

Computational Optimization and Applications
An adaptive Bayesian pruning for neural networks in a non-stationary environment

Neural Computation
Dynamic Learning with the EM Algorithm for Neural Networks

Journal of VLSI Signal Processing Systems
Exchange-Rates Forecasting: A Hybrid Algorithm Based onGenetically Optimized Adaptive Neural Networks

Computational Economics
Training fuzzy systems with the extended Kalman filter

Fuzzy Sets and Systems - Fuzzy systems
Faster Convergence and Improved Performance in Least-Squares Training of Neural Networks for Active Sound Cancellation

ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
Self-organised evolutionary neural networks: algorithms and applications

Highly parallel computaions
On-line identification and reconstruction of finite automata with generalized recurrent neural networks

Neural Networks
Dual extended Kalman filtering in recurrent neural networks

Neural Networks
Sequential Monte Carlo Methods to Train Neural Network Models

Neural Computation
Hierarchical Bayesian Models for Regularization in Sequential Learning

Neural Computation
Stock Index Prediction Based on Adaptive Training and Pruning Algorithm

ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Part II--Advances in Neural Networks
The Local True Weight Decay Recursive Least Square Algorithm

Neural Information Processing
Nonlinear Bayesian Filters for Training Recurrent Neural Networks

MICAI '08 Proceedings of the 7th Mexican International Conference on Artificial Intelligence: Advances in Artificial Intelligence
Training ANFIS as an identifier with intelligent hybrid stable learning algorithm based on particle swarm optimization and extended Kalman filter

Fuzzy Sets and Systems
An Adaptive Recursive Least Square Algorithm for Feed Forward Neural Network and Its Application

ICIC '07 Proceedings of the 3rd International Conference on Intelligent Computing: Advanced Intelligent Computing Theories and Applications. With Aspects of Artificial Intelligence
An adaptive speed controller for induction motor drives using adaptive neuro-fuzzy inference system

ICIC'07 Proceedings of the intelligent computing 3rd international conference on Advanced intelligent computing theories and applications
Memory-efficient fully coupled filtering approach for observational model building

IEEE Transactions on Neural Networks
On the universal approximation theorem of fuzzy neural networks with random membership function parameters

ISNN'05 Proceedings of the Second international conference on Advances in Neural Networks - Volume Part I
A Neuro-Fuzzy Identification of ECG Beats

Journal of Medical Systems
Nonlinear single layer neural network training algorithm for incremental, nonstationary and distributed learning scenarios

Pattern Recognition
A new constructive neural network method for noise processing and its application on stock market prediction

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The training of feedforward networks using the conventional back propagation algorithm is plagued by slow convergence and misadjustment. In this paper, we apply optimal filtering techniques to train feedforward networks in the standard supervised learning framework. We consider first the global problem of computing the synaptic weights all simultaneously, and then develop the idea of local linearization and partitioning. We present three algorithms which are computationally more expensive than standard back propagation, but local at the neuron level. These algorithms do not incorporate any tunable parameters and show excellent performance in comparison to the expensive approach of the global Extended Kalman Algorithm in terms of speed of convergence and quality of solution obtained on three benchmark problems.