The paper overviews results dealing with the approximation capabilities of neural networks, and bounds on the size of threshold gate circuits. Based on an explicit numerical algorithm for Kolmogorov's superpositions we will show that minimum size neural networks - for implementing any Boolean function - have the identity function as the activation function. Conclusions and several comments on the required precision are ending the paper.
|Number of pages||6|
|Journal||Intelligent Engineering Systems Through Artificial Neural Networks|
|Publication status||Published - 1998|
ASJC Scopus subject areas