Title :
Convergence of back-propagation in neural networks using a log-likelihood cost function
Author :
Holt, M.J.J. ; Semnani, S.
Author_Institution :
Dept. of Electron. & Electr. Eng., Loughborough Univ. of Technol., UK
Abstract :
A variation of the back-propagation algorithm is described, using a log-likelihood cost function. Appropriate choices of learning parameters are discussed. An example is given where the range of initial weights leading to proper convergence is increased, and the number of iterations required is significantly reduced.
Keywords :
convergence; neural nets; back-propagation algorithm; convergence of back-propagation; initial weights; iterations reduction; log-likelihood cost function; neural networks;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19901270