## Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions

- Guang-Bin Huang, Haroon Atique Babri
- IEEE Trans. Neural Networks
- 1998

Highly Influenced

@article{Sartori1991ASM, title={A simple method to derive bounds on the size and to train multilayer neural networks}, author={Michael A. Sartori and Panos J. Antsaklis}, journal={IEEE transactions on neural networks}, year={1991}, volume={2 4}, pages={467-71} }

- Published 1991 in IEEE Trans. Neural Networks
DOI:10.1109/72.88168

A new derivation is presented for the bounds on the size of a multilayer neural network to exactly implement an arbitrary training set; namely the training set can be implemented with zero error with two layers and with the number of the hidden-layer neurons equal to #1>/= p-1. The derivation does not require the separation of the input space by particular hyperplanes, as in previous derivations. The weights for the hidden layer can be chosen almost arbitrarily, and the weights for the output… CONTINUE READING

54 Citations

5 References

Similar Papers

Showing 1-5 of 5 references

Highly Influential

Highly Influential