Title :
An invariance property of neural networks
Author :
Gish, Herbert ; Siu, Manhung
Author_Institution :
BBN Syst. & Technol. Corp., Cambridge, MA, USA
Abstract :
It is often the case that one wants to apply a neural network classifier, trained with a particular mix of the training classes, to a situation where the classes occur in a different proportion. The originally trained network will not be appropriate for the new situation. The authors show that only a single weight of the network needs to be modified to accommodate the network to the new situation. The other weights are invariant to the change in mix
Keywords :
invariance; learning (artificial intelligence); neural nets; pattern classification; classifier; invariance property; neural networks; training classes; weights; Equations; Neural networks; Testing;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1994. ICASSP-94., 1994 IEEE International Conference on
Conference_Location :
Adelaide, SA
Print_ISBN :
0-7803-1775-0
DOI :
10.1109/ICASSP.1994.389599
