TY - GEN
T1 - Incremental learning for multitask pattern recognition problems
AU - Ozawa, Seiichi
AU - Roy, Asim
PY - 2008/12/1
Y1 - 2008/12/1
N2 - This paper presents a learning model of multitask pattern recognition (MTPR) which is constructed by several neural classifiers, long-term memories, and the detector of task changes. In the MTPR problem, several multi-class classification tasks are sequentially given to the learning model without notifying their task categories. This implies that the learning model is supposed to detect task changes by itself and to utilize the knowledge on the previous tasks for learning of new tasks. In addition, the learning model must acquire knowledge of multiple tasks incrementally without unexpected forgetting under the condition that not only tasks but also training samples are sequentially given. The proposed model is evaluated for two artificial MTPR problem. In the experiments, we verify that the proposed model can acquire and accumulate task knowledge very stably and the speed of knowledge acquisition for new tasks is enhanced by transferring knowledge.
AB - This paper presents a learning model of multitask pattern recognition (MTPR) which is constructed by several neural classifiers, long-term memories, and the detector of task changes. In the MTPR problem, several multi-class classification tasks are sequentially given to the learning model without notifying their task categories. This implies that the learning model is supposed to detect task changes by itself and to utilize the knowledge on the previous tasks for learning of new tasks. In addition, the learning model must acquire knowledge of multiple tasks incrementally without unexpected forgetting under the condition that not only tasks but also training samples are sequentially given. The proposed model is evaluated for two artificial MTPR problem. In the experiments, we verify that the proposed model can acquire and accumulate task knowledge very stably and the speed of knowledge acquisition for new tasks is enhanced by transferring knowledge.
UR - http://www.scopus.com/inward/record.url?scp=60649105757&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=60649105757&partnerID=8YFLogxK
U2 - 10.1109/ICMLA.2008.70
DO - 10.1109/ICMLA.2008.70
M3 - Conference contribution
AN - SCOPUS:60649105757
SN - 9780769534954
T3 - Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008
SP - 747
EP - 751
BT - Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008
T2 - 7th International Conference on Machine Learning and Applications, ICMLA 2008
Y2 - 11 December 2008 through 13 December 2008
ER -