Title :
Learning in competitively inhibited neural nets
Author :
Lemmon, Michael ; Kumar, B. V K Vijaya
Abstract :
The competitively inhibited neural network (CINN) is a competitive learning paradigm which is modeled by a collection of ordinary differential equations. A sliding threshold condition has been derived for determining the activity of a CINN neuron. This condition allows the development of a mathematical model for CINN learning. The model is a nonlinear diffusion equation whose solution quantitatively characterizes the learning process. Simulation experiments have validated this model
Keywords :
digital simulation; learning systems; neural nets; CINN learning; CINN neuron; competitive learning paradigm; nonlinear diffusion equation; ordinary differential equations; sliding threshold condition;
Conference_Titel :
Neural Networks, 1990., 1990 IJCNN International Joint Conference on
Conference_Location :
San Diego, CA, USA
DOI :
10.1109/IJCNN.1990.137885
