1Dept. of Electron. and Comput. Eng., Pretoria Univ.
A new stochastic technique for training neural-net classifiers is superior for large datasets. Standard deterministic methods like variable metric and conjugate gradient show similar convergence rates.
You might also read
Articles linked to this work by shared authors, journal, and citation graph.
Area of Science:
Background:
Purpose of the Study:
Main Methods:
Main Results:
Conclusions: