A Sigma-Pi-Sigma Neural Network (SPSNN)
Neural Processing Letters
Direct Estimation of Polynomial Densities in Generalized RBF Networks Using Moments
ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
Synthesis of Neural Network-Based Approximators with Heterogeneous Architecture
Programming and Computing Software
Benchmarking a Reduced Multivariate Polynomial Pattern Classifier
IEEE Transactions on Pattern Analysis and Machine Intelligence
Constructive Incremental Learning from Only Local Information
Neural Computation
Root finding and approximation approaches through neural networks
ACM SIGSAM Bulletin
Dynamic Ridge Polynomial Neural Networks for multi-step financial time-series prediction
International Journal of Intelligent Systems Technologies and Applications
Dynamic Ridge Polynomial Neural Networks in Exchange Rates Time Series Forecasting
ICANNGA '07 Proceedings of the 8th international conference on Adaptive and Natural Computing Algorithms, Part II
Speech prediction using higher order neural networks
IIT'09 Proceedings of the 6th international conference on Innovations in information technology
A Hybrid Higher Order Neural Classifier for handling classification problems
Expert Systems with Applications: An International Journal
Expert Systems with Applications: An International Journal
Polynomial network classifier with discriminative feature extraction
SSPR'06/SPR'06 Proceedings of the 2006 joint IAPR international conference on Structural, Syntactic, and Statistical Pattern Recognition
Hi-index | 0.01 |
This paper presents a polynomial connectionist network called ridge polynomial network (RPN) that can uniformly approximate any continuous function on a compact set in multidimensional input space R d, with arbitrary degree of accuracy. This network provides a more efficient and regular architecture compared to ordinary higher-order feedforward networks while maintaining their fast learning property. The ridge polynomial network is a generalization of the pi-sigma network and uses a special form of ridge polynomials. It is shown that any multivariate polynomial can be represented in this form, and realized by an RPN. Approximation capability of the RPN's is shown by this representation theorem and the Weierstrass polynomial approximation theorem. The RPN provides a natural mechanism for incremental network growth. Simulation results on a surface fitting problem, the classification of high-dimensional data and the realization of a multivariate polynomial function are given to highlight the capability of the network. In particular, a constructive learning algorithm developed for the network is shown to yield smooth generalization and steady learning