Title :
A self-training, self-repairing back-propagation environment
Author_Institution :
Center for Brain Res., Radford Univ., VA, USA
Abstract :
The author introduces a series of novel approaches to backpropagation: (1) the use of logic forms (classical, modal, and nonmonotonic) as training tools; (2) the construction of new nets through the responses of logically trained nets (weight sets); (3) the use of N2 as a reset mechanism for impermissibly slow or false responses by subnets; and (4) the retraining of failing subnets by the logically trained nets. A biologically plausible basis for the system is offered
Keywords :
backpropagation; learning (artificial intelligence); neural nets; N2; biologically plausible basis; logic forms; logically trained nets; nonmonotonic; reset mechanism; self-repairing back-propagation environment; self-training; training tools; Biological neural networks; Boolean functions; Employment; Frequency; Humans; Logic; Stability; Testing;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.287078
