On analog implementations of discrete neural networks
The paper will show that in order to obtain minimum size neural networks (i.e., size-optimal) for implementing any Boolean function, the nonlinear activation function of the neutrons has to be the identity function. The authors shall shortly present many results dealing with the approximation capabilities of neural networks, and detail several bounds on the size of threshold gate circuits. Based on a constructive solution for Kolmogorov`s superpositions they will show that implementing Boolean functions can be done using neurons having an identity nonlinear function. It follows that size-optimal solutions can be obtained only using analog circuitry. Conclusions, and several comments on the required precision are ending the paper.
- Research Organization:
- Los Alamos National Lab., Div. of Space and Atmospheric Sciences, NM (United States)
- Sponsoring Organization:
- USDOE Assistant Secretary for Management and Administration, Washington, DC (United States)
- DOE Contract Number:
- W-7405-ENG-36
- OSTI ID:
- 677167
- Report Number(s):
- LA-UR--98-1609; CONF-980942--; ON: DE99000763
- Country of Publication:
- United States
- Language:
- English
Similar Records
On Kolmogorov's superpositions and Boolean functions
Larger bases and mixed analog/digital neural nets