Implementing size-optimal discrete neural networks require analog circuitry
Conference
·
OSTI ID:291117
This paper starts by overviewing results dealing with the approximation capabilities of neural networks, as well as bounds on the size of threshold gate circuits. Based on a constructive solution for Kolmogorov`s superpositions the authors show that implementing Boolean functions can be done using neurons having an identity transfer function. Because in this case the size of the network is minimized, it follows that size-optimal solutions for implementing Boolean functions can be obtained 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 Office of Energy Research, Washington, DC (United States)
- DOE Contract Number:
- W-7405-ENG-36
- OSTI ID:
- 291117
- Report Number(s):
- LA-UR--98-1702; CONF-980911--; ON: DE99000650
- Country of Publication:
- United States
- Language:
- English
Similar Records
On analog implementations of discrete neural networks
On Kolmogorov's superpositions and Boolean functions
Larger bases and mixed analog/digital neural nets
Conference
·
Mon Nov 30 23:00:00 EST 1998
·
OSTI ID:677167
On Kolmogorov's superpositions and Boolean functions
Conference
·
Wed Dec 30 23:00:00 EST 1998
·
OSTI ID:314133
Larger bases and mixed analog/digital neural nets
Conference
·
Wed Dec 30 23:00:00 EST 1998
·
OSTI ID:334354