書誌事項
- タイトル別名
-
- 誤差逆伝播ネットワークによる重ね書き記憶
この論文をさがす
抄録
application/pdf
We propose a novel neural network for incremental learning tasks where networks are required to learn new knowledge without forgetting the old one. An essential core of the proposed neural learning structure is a transferring scheme from short-term memory (STM) into long-term memory (LTM) as in brains by using dynamic changing weights. As the number of LTMs increases, a new network structure is superimposed on the previous one without disturbing the past LTMs by introducing a lateral inhibition mechanism. Superiority of the proposed neural structure to the conventional backpropagation networks is proven with respect to the learning ability.
紀要類(bulletin)
671882 bytes
収録刊行物
-
- 東北大学医療技術短期大学部紀要 = Bulletin of College of Medical Sciences, Tohoku University
-
東北大学医療技術短期大学部紀要 = Bulletin of College of Medical Sciences, Tohoku University 12 (2), 111-120, 2003-07-31
東北大学医療技術短期大学部
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1050282677703639552
-
- NII論文ID
- 120000778536
- 110000964034
-
- NII書誌ID
- AN1037430X
-
- ISSN
- 09174435
-
- HANDLE
- 10097/33818
-
- NDL書誌ID
- 6666129
-
- 本文言語コード
- en
-
- 資料種別
- departmental bulletin paper
-
- データソース種別
-
- IRDB
- NDL
- CiNii Articles