Abstract:
We present a novel MLP-type neural network based on hyperbolic numbers $the hyperbolic multilayer perceptron (HMLP). The neurons of the HMLP compute 2D-hyperbolic orthogo...Show MoreMetadata
Abstract:
We present a novel MLP-type neural network based on hyperbolic numbers $the hyperbolic multilayer perceptron (HMLP). The neurons of the HMLP compute 2D-hyperbolic orthogonal transformations as weight propagation functions. The HMLP can therefore be seen as the hyperbolic counterpart of the known complex MLP. The HMLP is proven to be a universal approximator. Furthermore, a suitable backpropagation algorithm for it is derived. It is shown by experiments that the HMLP can learn tasks with underlying hyperbolic properties much more accurately and efficiently than a complex MLP and an ordinary MLP.
Date of Conference: 27-27 July 2000
Date Added to IEEE Xplore: 06 August 2002
Print ISBN:0-7695-0619-4
Print ISSN: 1098-7576