No label defined (Q4493288)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 1484335
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | No label defined |
scientific article; zbMATH DE number 1484335 |
Statements
3 August 2000
0 references
neural network learning problem
0 references
linear programming problem
0 references
duality
0 references
0.8424550294876099
0 references
0.7713720202445984
0 references
0.7706890106201172
0 references
0.7524927258491516
0 references
The neural network learning problem is formulated as the following LP-problem: Find \(x_j \geq 0\), \(j=1,\dots,n+1\) which satisfy the \(n^2 + 1\) constraints: \[ x_i-a_{si}x_s + h_i x_{n+1} \geq 0, \quad i \neq s,\;i,s=1,\dots,n, \] \[ x_i - x_{n+1} \geq 0, \quad i = 1,\dots,n, \] \[ x_1 + x_2 + \dots + x_n = 1 \] and maximize the linear form \(z = x_{n+1}\); all the \(a_{si}\), \(h_i\), \(0 \leq a_{si} < h_i \leq 1\) are assumed to be known. The authors consider directly the above stated LP-problem and characterize the extreme points of the set of feasible solutions. The process of solving the considered LP-problem seems effective, because the formulae and the computations are particularly simple.
0 references