ISSN:
1573-773X
Keywords:
neural networks
;
learning
;
minimal distance methods
;
similarity-based methods
;
machine learning
;
interpretation of neural functions
;
classification
Source:
Springer Online Journal Archives 1860-2000
Topics:
Computer Science
Notes:
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.
Type of Medium:
Electronic Resource
URL:
http://dx.doi.org/10.1023/A:1018728407584
Permalink