Name
Abstract | ||
|---|---|---|
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. |
Year | DOI | Venue |
|---|---|---|
2006 | 10.1016/j.camwa.2005.07.012 | Computers & Mathematics with Applications |
Keywords | Field | DocType |
feedforward neural network,univariate polynomial,neural network,multivariate polynomial equation,neural networks,roots of polynomials,real solution,number of zeros.,high accuracy,training set,test set,real root,number of zeros | Stochastic neural network,Recurrent neural network,Artificial intelligence,Artificial neural network,Mathematical optimization,Feedforward neural network,Algorithm,Probabilistic neural network,Types of artificial neural networks,Univariate,Machine learning,Mathematics,Test set | Journal |
Volume | Issue | ISSN |
51 | 3-4 | Computers and Mathematics with Applications |
Citations | PageRank | References |
3 | 0.43 | 15 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| B. Mourrain | 1 | 35 | 3.88 |
| N. G. Pavlidis | 2 | 219 | 9.04 |
| D.K. Tasoulis | 3 | 490 | 29.51 |
| M.N. Vrahatis | 4 | 1740 | 151.65 |