INVESTIGADORES
DIAMBRA Luis Anibal
artículos
Título:
Neural network training without spurious minima
Autor/es:
L. DIAMBRA; A. PLASTINO
Revista:
Physical Review E
Editorial:
AMERICAN PHYSICAL SOCIETY
Referencias:
Año: 1996 vol. 53 p. 5190 - 5193
Resumen:
In training student perceptions, recourse to information theory concepts allows one to select the best working
hypothesis and obtain an exact solution for the associated probability distribution. We apply this training
scheme to perceptions with binary weights and show that no phase transition ensues. By recourse to our
approach fast learning is guaranteed and trapping by spurious local minima is avoided.