A function estimation approach to sequential learning with neural networks

Authors:
Visakan Kadirkamanathan;Mahesan Niranjan
Affiliations:
-;-
Venue:
Neural Computation
Year:
1993

Citing 0
Cited 62

A sequential learning scheme for function approximation using minimal radial basis function neural networks

Neural Computation
Prediction of Chaotic Time-Series with a Resource-Allocating RBF Network

Neural Processing Letters
A fast learning algorithm for parismonious fuzzy neural systems

Fuzzy Sets and Systems - Information processing
Identification of nonlinear discrete-time systems using raised-cosine radial basis function networks

International Journal of Systems Science
Robust Full Bayesian Learning for Radial Basis Networks

Neural Computation
A Measurement Fusion Method for Nonlinear System Identification Using a Cooperative Learning Algorithm

Neural Computation
A sequential algorithm for feed-forward neural networks with optimal coefficients and interacting frequencies

Neurocomputing
Improved GAP-RBF network for classification problems

Neurocomputing
A sequential multi-category classifier using radial basis function networks

Neurocomputing
Pruning with replacement on limited resource allocating networks by f-projections

Neural Computation
Regularization in the selection of radial basis function centers

Neural Computation
Automated cross-modal mapping in robotic eye/hand systems using plastic radial basis function networks

Connection Science
An On-Line Learning Radial Basis Function Network and Its Application

ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks
A Sequential Learning Algorithm for RBF Networks with Application to Ship Inverse Control

ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks
Model selection approaches for non-linear system identification: a review

International Journal of Systems Science
Hybrid learning-based neuro-fuzzy inference system: a new approach for system modeling

International Journal of Systems Science
Subsonic Tests of a Flush Air Data Sensing System Applied to a Fixed-Wing Micro Air Vehicle

Journal of Intelligent and Robotic Systems
CMAC-based neuro-fuzzy approach for complex system modeling

Neurocomputing
Simultaneous input variable and basis function selection for RBF networks

Neurocomputing
A Versatile Hyper-Ellipsoidal Basis Function for Function Approximation in High Dimensional Space

ISNN '09 Proceedings of the 6th International Symposium on Neural Networks on Advances in Neural Networks
An Online Self-constructing Fuzzy Neural Network with Restrictive Growth

ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part II
Pipelined Genetic Algorithm Initialized RAN Based RBF Modulation Classifier

ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part II
On-Line Tuning of a Neural PID Controller Based on Variable Structure RBF Network

ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part II
A hybrid learning algorithm with a similarity-based pruning strategy for self-adaptive neuro-fuzzy systems

Applied Soft Computing
A fast and accurate online self-organizing scheme for parsimonious fuzzy neural networks

Neurocomputing
Sequential Hierarchical Pattern Clustering

PRIB '09 Proceedings of the 4th IAPR International Conference on Pattern Recognition in Bioinformatics
Evolving logic networks with real-valued inputs for fast incremental learning

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics - Special issue on human computing
A growing and pruning method for radial basis function networks

IEEE Transactions on Neural Networks
A constructive enhancement for online sequential extreme learning machine

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Adaptive neural model-based fault tolerant control for multi-variable processes

Engineering Applications of Artificial Intelligence
Sequential Adaptive Fuzzy Inference System (SAFIS) for nonlinear system identification and prediction

Fuzzy Sets and Systems
Genetic algorithms for MLP neural network parameters optimization

CCDC'09 Proceedings of the 21st annual international conference on Chinese control and decision conference
A fast and compact fuzzy neural network for online extraction of fuzzy rules

CCDC'09 Proceedings of the 21st annual international conference on Chinese control and decision conference
An intelligent PID controller based on variable structure radial basis function network

CCDC'09 Proceedings of the 21st annual international conference on Chinese control and decision conference
Online adaptive radial basis function networks for robust object tracking

Computer Vision and Image Understanding
Computationally efficient sequential learning algorithms for direct link resource-allocating networks

Neurocomputing
Dynamic temperature modeling of continuous annealing furnace using GGAP-RBF neural network

Neurocomputing
Online training for single hidden-layer Online training for single hidden-layer

CIRA'09 Proceedings of the 8th IEEE international conference on Computational intelligence in robotics and automation
eFSM: a novel online neural-fuzzy semantic memory model

IEEE Transactions on Neural Networks
A BCM theory of meta-plasticity for online self-reorganizing fuzzy-associative learning

IEEE Transactions on Neural Networks
A new online learning algorithm for structure-adjustable extreme learning machine

Computers & Mathematics with Applications
POFGEC: growing neural network of classifying potential function generators

International Journal of Knowledge Engineering and Soft Data Paradigms
An evolving-onstruction scheme for fuzzy systems

IEEE Transactions on Fuzzy Systems
A sequential learning algorithm for self-adaptive resource allocation network classifier

Neurocomputing
Dynamic fuzzy neural networks modeling and adaptive backstepping tracking control of uncertain chaotic systems

Neurocomputing
Incremental learning with multi-level adaptation

Neurocomputing
A generalized online self-constructing fuzzy neural network

ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part II
A Generalized Ellipsoidal Basis Function Based Online Self-constructing Fuzzy Neural Network

Neural Processing Letters
Regularized online sequential learning algorithm for single-hidden layer feedforward neural networks

Pattern Recognition Letters
Adaptive identification of chaotic systems and its applications in chaotic communications

ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part II
Adaptive point-cloud surface interpretation

CGI'06 Proceedings of the 24th international conference on Advances in Computer Graphics
A new on-line modeling approach to nonlinear dynamic systems

ISNN'06 Proceedings of the Third international conference on Advnaces in Neural Networks - Volume Part II
Multiple models adaptive control based on RBF neural network dynamic compensation

ISNN'05 Proceedings of the Second international conference on Advances in Neural Networks - Volume Part III
Brief paper: Dual adaptive control of nonlinear stochastic systems using neural networks

Automatica (Journal of IFAC)
Neuro-controller design for nonlinear fighter aircraft maneuver using fully tuned RBF networks

Automatica (Journal of IFAC)
ABR traffic management using minimal resource allocation (neural) networks

Computer Communications
The automatic model selection and variable kernel width for RBF neural networks

Neurocomputing
Nonlinear model identification and adaptive control of CO2 sequestration process in saline aquifers using artificial neural networks

Applied Soft Computing
An improved learning scheme for extracting t-s fuzzy rules from data samples

ISNN'13 Proceedings of the 10th international conference on Advances in Neural Networks - Volume Part II
A growing and pruning sequential learning algorithm of hyper basis function neural network for function approximation

Neural Networks
Dynamic Fuzzy Neural Network Based Learning Algorithms for Ocular Artefact Reduction in EEG Recordings

Neural Processing Letters
Online ship roll motion prediction based on grey sequential extreme learning machine

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper, we investigate the problem of optimal sequentiallearning, viewed as a problem of estimating an underlying functionsequentially rather than estimating a set of parameters of theneural network. First, we arrive at a suboptimal solution to thesequential estimate that can be mapped by a growing gaussian radialbasis function (GaRBF) network. This network adds hidden units foreach observation. The function space approach in which theestimates are represented as vectors in a function space is used indeveloping a growth criterion to limit its growth. A simplificationof the criterion leads to two joint criteria on the distance of thepresent pattern and the existing unit centers in the input spaceand on the approximation error of the network for the givenobservation to be satisfied together. This network is similar tothe resource allocating network (RAN) (Platt 1991a) and hence RANcan be interpreted from a function space approach to sequentiallearning. Second, we present an enhancement to the RAN. The RANeither allocates a new unit based on the novelty of an observationor adapts the network parameters by the LMS algorithm. The functionspace interpretation of the RAN lends itself to an enhancement ofthe RAN in which the extended Kalman filter (EKF) algorithm is usedin place of the LMS algorithm. The performance of the RAN and theenhanced network are compared in the experimental tasks of functionapproximation and time-series prediction demonstrating the superiorperformance of the enhanced network with fewer number of hiddenunits. The approach adopted here has led us toward the minimalnetwork required for a sequential learning problem.