|국가/구분||United States(US) Patent 등록|
|미국특허분류(USC)||395/23 ; 395/22 ; 395/24 ; 395/27|
|발명자 / 주소|
|출원인 / 주소|
|인용정보||피인용 횟수 : 17 인용 특허 : 0|
The present invention provides a system and method for supervised training of a neural network. A neural network architecture and training method is disclosed that is a modification of an ARTMAP architecture. The modified ARTMAP network is an efficient and robust paradigm which has the unique property of incremental supervised learning. Furthermore, the modified ARTMAP network has the capability of removing undesired knowledge that has previously been learned by the network.
A computer-implemented method of training and testing a modified ARTMAP neural network, wherein the modified ARTMAP neural network has an ART module that accepts an input pattern and has a first layer and a second layer, and a Map field, connected to said ART module, that accepts a target output pattern, the computer-implemented method comprising: (1) presenting an input pattern to be learned to the modified ARTMAP neural network; (2) determining a set of activations for the first layer; (3) determining a set of matching scores for the second layer; (4) ...