Preferred Language
Articles
/
ijs-1576
Monotone Approximation by Quadratic Neural Network of Functions in Lp Spaces for p<1
...Show More Authors

Some researchers are interested in using the flexible and applicable properties of quadratic functions as activation functions for FNNs. We study the essential approximation rate of any Lebesgue-integrable monotone function by a neural network of quadratic activation functions. The simultaneous degree of essential approximation is also studied. Both estimates are proved to be within the second order of modulus of smoothness.

Scopus Crossref
View Publication Preview PDF
Quick Preview PDF