ISSN:
1573-773X
Schlagwort(e):
neural networks
;
learning
;
minimal distance methods
;
similarity-based methods
;
machine learning
;
interpretation of neural functions
;
classification
Quelle:
Springer Online Journal Archives 1860-2000
Thema:
Informatik
Notizen:
Abstract Multilayer Perceptrons (MLPs) use scalar products to compute weighted activation of neurons providing decision borders using combinations of soft hyperplanes. The weighted fun-in activation function may be replaced by a distance function between the inputs and the weights, offering a natural generalization of the standard MLP model. Non-Euclidean distance functions may also be introduced by normalization of the input vectors into an extended feature space. Both approaches influence the shapes of decision borders dramatically. An illustrative example showing these changes is provided.
Materialart:
Digitale Medien
URL:
http://dx.doi.org/10.1023/A:1018728407584
Permalink