A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2006; you can also visit the original URL.
The file type is application/pdf
.
Training a Sigmoidal Node Is Hard
1999
Neural Computation
This paper proves that the task of computing near{optimal weights for sigmoidal nodes under the L 1 regression norm is NP{Hard. For the special case where the sigmoid is piecewise{linear we p r o ve a s l i g h tly stronger result, namely that computing the optimal weights is NP{Hard. These results parallel that for the one{node pattern recognition problem, namely that determining the optimal weights for a threshold logic node is also intractable. Our results have important consequences for
doi:10.1162/089976699300016449
fatcat:hdzoobbitjb6bginlypwmfjtnu