Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
4615804 | Journal of Mathematical Analysis and Applications | 2014 | 7 Pages |
Abstract
In the current note, we show that a two hidden layer neural network with d inputs, d neurons in the first hidden layer, 2d+22d+2 neurons in the second hidden layer and with a specifically constructed sigmoidal and infinitely differentiable activation function can approximate any continuous multivariate function with arbitrary accuracy.
Related Topics
Physical Sciences and Engineering
Mathematics
Analysis
Authors
Vugar E. Ismailov,