On the quadratic extension of the canonical piecewise-linear network
- 2 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 316-319
- https://doi.org/10.1109/iscas.1992.229950
Abstract
The network on the canonical piecewise-linear representation (CPWL), compared to conventional mapping networks such as the backpropagation network and the radial basis network, has advantages in both learning, and implementation aspects. An extension of the CPWL network called the network of canonical piecewise-quadratic representation with linear partitions (CPWQ-L) is proposed. The CPWQ-L network shares the advantages of the CPWL network in explicitly and compactly realizing a spline approximation of nonlinear functions, while it extends the approximation capability of the latter at a low cost in computation and implementation. Examples of computer simulations are presented to demonstrate the superiority of the CPWQ-L network in some applications.Keywords
This publication has 5 references indexed in Scilit:
- A multilayer neural network with piecewise-linear structure and back-propagation learningIEEE Transactions on Neural Networks, 1991
- Arbitrary nonlinearity is sufficient to represent all functions by neural networks: A theoremNeural Networks, 1991
- Adaptive nonlinear digital filter with canonical piecewise-linear structureIEEE Transactions on Circuits and Systems, 1990
- Layered neural nets for pattern recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1988
- Canonical piecewise-linear representationIEEE Transactions on Circuits and Systems, 1988