Mixture density network training by computation in parameter space

Evans, David J. (1998). Mixture density network training by computation in parameter space. Technical Report. Aston University, Birmingham.

Abstract

Training Mixture Density Network (MDN) configurations within the NETLAB framework takes time due to the nature of the computation of the error function and the gradient of the error function. By optimising the computation of these functions, so that gradient information is computed in parameter space, training time is decreased by at least a factor of sixty for the example given. Decreased training time increases the spectrum of problems to which MDNs can be practically applied making the MDN framework an attractive method to the applied problem solver.

Divisions: Engineering & Applied Sciences > Computer science
Engineering & Applied Sciences > Computer science research group
Uncontrolled Keywords: Training Mixture Density Network,error function,gradient information,parameter space,applied problem solver
Published Date: 1998
Authors: Evans, David J.

Download

Export / Share Citation


Statistics

Additional statistics for this record