Abstract | ||
---|---|---|
A connection is drawn between rational functions, the realization theory of dynamical systems, and feedforward neural networks. This allows us to parametrize single hidden layer scalar neural networks with (almost) arbitrary analytic activation functions in terms of strictly proper rational functions. Hence, we can solve the uniqueness of parametrization problem for such networks. |
Year | Venue | Keywords |
---|---|---|
1992 | NIPS | neural network |
Field | DocType | ISBN |
Uniqueness,Mathematical optimization,Feedforward neural network,Parametrization,Computer science,Scalar (physics),Dynamical systems theory,Artificial neural network,Rational function | Conference | 1-55860-274-7 |
Citations | PageRank | References |
0 | 0.34 | 1 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Uwe Helmke | 1 | 337 | 42.53 |
Robert C. Williamson | 2 | 4191 | 755.22 |