Title :
The generalized AdaTron algorithm
Author :
Nachbar, P. ; Nossek, J.A. ; Strobl, J.
Author_Institution :
Inst. for Network Theory & Circuit Design, Tech. Univ. of Munich, Germany
Abstract :
The AdaTron algorithm can find the most insensitive weights of a perceptron or attractor network with respect to the usual Euclidean norm. The authors define various notions of robustness for q-norms as appropriate for perceptrons or attractor networks. By extending the so-called AdaTron theorem, they are able to generalize the AdaTron algorithm, which then finds the most insensitive weights with respect to an arbitrary q-norm
Keywords :
learning (artificial intelligence); pattern recognition; perceptrons; Euclidean norm; attractor network; generalized AdaTron algorithm; most insensitive weights; perceptron; q-norms; robustness; Circuit synthesis; Electronic mail; Neural networks; Neurons; Quadratic programming; Robustness;
Conference_Titel :
Circuits and Systems, 1993., ISCAS '93, 1993 IEEE International Symposium on
Conference_Location :
Chicago, IL
Print_ISBN :
0-7803-1281-3
DOI :
10.1109/ISCAS.1993.394184
