Title :
On-line learning trough simple perceptron learning with a margin
Author :
Hara, Kazuyuki ; Okada, Masato
Author_Institution :
Tokyo Metropolitan Coll. of Technol., Japan
Abstract :
We analyze a learning method that uses a margin k a la Gardner for simple perceptron learning. This method corresponds to perceptron learning when k = 0, and to Hebbian learning when k → ∞. Nevertheless, we found that the generalization ability of the method was superior to that of the perceptron and the Hebbian methods at an early stage of learning.
Keywords :
Hebbian learning; generalisation (artificial intelligence); perceptrons; Hebbian learning; generalization ability; learning method; margin; online learning; simple perceptron learning; Biological neural networks; Educational institutions; Feedforward neural networks; Hebbian theory; Image analysis; Information analysis; Learning systems; Neural networks; Support vector machine classification; Support vector machines;
Conference_Titel :
Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on
Print_ISBN :
981-04-7524-1
DOI :
10.1109/ICONIP.2002.1202151
