Name
Abstract | ||
|---|---|---|
In this paper we establish a relationship between regularization theory and morphological shared-weight neural networks (MSNN). We show that a certain class of morphological shared-weight neural networks with no hidden units can be viewed as regularization neural networks. This relationship is established by showing that this class of MSNNs are solutions of regularization problems. This requires deriving the Fourier transforms of the min and max operators. The Fourier transforms of min and max operators are derived using generalized functions because they are only defined in that sense. |
Year | DOI | Venue |
|---|---|---|
2000 | 10.1016/S0031-3203(99)00156-9 | Pattern Recognition |
Keywords | Field | DocType |
Morphology,Morphological Shared-weight Neural Network,Regularization Theory,Regularization Network,Hit–miss transform | Fourier transform,Regularization (mathematics),Operator (computer programming),Artificial intelligence,Artificial neural network,Generalized function,Regularization theory,Machine learning,Mathematics,Regularization perspectives on support vector machines | Journal |
Volume | Issue | ISSN |
33 | 6 | 0031-3203 |
Citations | PageRank | References |
26 | 2.39 | 5 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Paul Gader | 1 | 1909 | 196.70 |
| Mohamed A. Khabou | 2 | 84 | 9.90 |
| Alexander Koldobsky | 3 | 28 | 4.41 |