Patent Number: 6,311,172

Title: Method for determination of weights, suitable for elimination, of a neural network using a computer

Abstract: The training phase of a neural network NN is stopped before an error function, which is to be minimized in the training phase, reaches a minimum (301). A first variable (EG) is defined using, for example, the optimal brain damage method or the optimal brain surgeon method, on the assumption that the error function is at the minimum. Furthermore, a second variable (ZG) is determined which provides an indication of the manner in which the value of the error function varies when a weight (w.sub.i) is removed from the neural network (NN). The first variable (EG) and the second variable (ZG) are used to classify the weight (w.sub.i) as being suitable or unsuitable for removal from the neural network (NN).

Inventors: Tresp; Volker (Munchen, DE), Zimmermann; Hans-Georg (Starnberg/Percha, DE), Neuneier; Ralph (Munchen, DE)

Assignee: Siemens Aktiengesellschaft

International Classification: G06F 17/00 (20060101); G06N 3/00 (20060101); G06N 3/08 (20060101); G06F 015/18 ()

Expiration Date: 10/30/2018