Creator:

Williams, Paul ; Duller, Andrew W.G.

Contributor:

Korbicz, Józef (1951- ) - red. ; Uciński, Dariusz - red.

Title:

On the robustness of learning in the multi-layer perceptron

Group publication title:

AMCS, volume 5 (1995)

Subject and Keywords:

sterowanie ; sterowanie-teoria ; sztuczna inteligencja ; matematyka stosowana ; informatyka

Abstract:

The back-propagation algorithm, for training multi-layer perceptrons tends to be slow to converge to a final solution and many methods have been proposed for improving this. One technique takes advantage of an alternative training error criterion, however, we show that this reduces the robustness of the learning in the presence of outliers in the input data. Two examples are used to show the characteristics of the learning methods, one a test problem and the other from a "real-world" problem.

Publisher:

Zielona Góra: Uniwersytet Zielonogórski

Date:

1995

Resource Type:

artykuł

Pages:

743-749

Source:

AMCS, volume 5, number 4 (1995) ; click here to follow the link

Language:

eng

License CC BY 4.0:

click here to follow the link

Rights:

Biblioteka Uniwersytetu Zielonogórskiego