Corpus ID: 16287444

Approximation by Superpositions of a Sigmoidal Function *

@inproceedings{Cybenkot2006ApproximationBS,
  title={Approximation by Superpositions of a Sigmoidal Function *},
  author={G Cybenkot},
  year={2006}
}
  • G Cybenkot
  • Published 2006
Abstr,,ct. In this paper we demonstrate that finite linear combinations of compositions of a fixed, univariate function and a set ofaffine functionals can uniformly approximate any continuous function of n real variables with support in the unit hypercube; only mild conditions are imposed on the univariate function. Our results settle an open question about representability in the class of single bidden layer neural networks. In particular, we show that arbitrary decision regions can be… Expand
2 Citations
Learnable Explicit Density for Continuous Latent Space and Variational Inference
  • 17
  • PDF
Understanding state-of-the-art material classification through deep visualization
  • PDF

References

SHOWING 1-10 OF 29 REFERENCES
On the approximate realization of continuous mappings by neural networks
  • 4,039
  • PDF
Construction of neural nets using the radon transform
  • 166
On representation and approximation of nonlinear systems
  • G. Palm
  • Mathematics
  • Biological Cybernetics
  • 2004
  • 39
Multilayer feedforward networks are universal approximators
  • 15,367
  • PDF
Classification capabilities of two-layer neural nets
  • 35
What Size Net Gives Valid Generalization?
  • 1,666
  • PDF
An introduction to computing with neural nets
  • 3,525
  • PDF
...
1
2
3
...