Limited weights neural networks: Very tight entropy based bounds
Conference
·
OSTI ID:527896
- Los Alamos National Lab., NM (United States)
- Wayne State Univ., Detroit, MI (United States). Vision and Neural Networks Lab.
Being given a set of m examples (i.e., data-set) from IR{sup n} belonging to k different classes, the problem is to compute the required number-of-bits (i.e., entropy) for correctly classifying the data-set. Very tight upper and lower bounds for a dichotomy (i.e., k = 2) will be presented, but they are valid for the general case.
- Research Organization:
- Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
- Sponsoring Organization:
- USDOE Assistant Secretary for Human Resources and Administration, Washington, DC (United States)
- DOE Contract Number:
- W-7405-ENG-36
- OSTI ID:
- 527896
- Report Number(s):
- LA-UR-97-294; CONF-970939-1; ON: DE97004781; TRN: 97:005163
- Resource Relation:
- Conference: SOCO `97: 2. international symposium on soft computing, fuzzy logic, artificial neural networks, and genetic algorithms, Nimes (France), 17-19 Sep 1997; Other Information: PBD: 1997
- Country of Publication:
- United States
- Language:
- English
Similar Records
Tight bounds on the size of neural networks for classification problems
Computing n-dimensional volumes of complexes: Application to constructive entropy bounds
Computations of entropy bounds: Multidimensional geometric methods
Conference
·
Sun Jun 01 00:00:00 EDT 1997
·
OSTI ID:527896
Computing n-dimensional volumes of complexes: Application to constructive entropy bounds
Conference
·
Sat Nov 01 00:00:00 EST 1997
·
OSTI ID:527896
Computations of entropy bounds: Multidimensional geometric methods
Conference
·
Sun Feb 01 00:00:00 EST 1998
·
OSTI ID:527896