Approximation capabilities of multilayer feedforward networks
Neural Networks
Some new results on neural network approximation
Neural Networks
Dynamical properties of learning process of weakly nonlinear and nonlinear neurons
Nonlinear Analysis: Real World Applications
Estimation of Numerical Dynamics Constants of a Weakly Nonlinear Neuron
PPAM '01 Proceedings of the th International Conference on Parallel Processing and Applied Mathematics-Revised Papers
Shadowing property in analysis of neural networks dynamics
Journal of Computational and Applied Mathematics - Special Issue: Proceedings of the 10th international congress on computational and applied mathematics (ICCAM-2002)
Recognition of two-dimensional representation of urban environment for autonomous flying agents
Expert Systems with Applications: An International Journal
Hi-index | 0.00 |
The purpose of the paper is to present solutions of some problems associated with implementations of a weakly nonlinear neuron. We give estimates between constants in the Feckan Theorem and relations guarantying the pseudo-orbit tracing property (POTP). Then, a weakly nonlinear neuron is applied to a XOR-like problem.