Multilayer feedforward networks are universal approximators
Neural Networks
Effective backpropagation training with variable stepsize
Neural Networks
Constrained Learning in Neural Networks: Application to Stable Factorization of 2-D Polynomials
Neural Processing Letters
A class of gradient unconstrained minimization algorithms with adaptive stepsize
Journal of Computational and Applied Mathematics
Globally Convergent Modification of the Quickprop Method
Neural Processing Letters
From linear to nonlinear iterative methods
Applied Numerical Mathematics
A neural root finder of polynomials based on root moments
Neural Computation
Improved heterogeneous distance functions
Journal of Artificial Intelligence Research
A constructive approach for finding arbitrary roots of polynomials by neural networks
IEEE Transactions on Neural Networks
Training feedforward networks with the Marquardt algorithm
IEEE Transactions on Neural Networks
An efficient constrained training algorithm for feedforward networks
IEEE Transactions on Neural Networks
Root finding and approximation approaches through neural networks
ACM SIGSAM Bulletin
Hi-index | 0.09 |
The ability of feedforward neural networks to identify the number of real roots of univariate polynomials is investigated. Furthermore, their ability to determine whether a system of multivariate polynomial equations has real solutions is examined on a problem of determining the structure of a molecule. The obtained experimental results indicate that neural networks are capable of performing this task with high accuracy even when the training set is very small compared to the test set.