Emergent on-line Learning: Towards Brain-style Computers

摘要：

Emergent learning is a new learning paradigm that is more like the learning mechanism of the human brain than conventional learning paradigms such as back-propagation teaming method. In emergent learning paradigm, learning α complex problem is emerged from learning α reasonable number of sub-problems. The key to the emergent learning is to use two simple emergent laws -whose junctions are to control both problem decomposition and module combination processes. In this paper,we introduce an emergent on-line learning paradigm and discuss its suitability for a model of brain-style computers.

作者: Bao-Liang Lu Michinori Ichikawa

作者单位: Lab. for Brain-Operative Device, RIKEN Brain Science Institute 2-1 Hirosawa, Wako-shi 351-0198, Japan

会议类型: 国际会议

会议名称: 8th International Conference on Neural Information Processing(ICONIP 2001)(第八届国际神经信息处理大会)

会议地点: 上海

会议语种:英文

页码: 693-696

在线出版日期: 2001-11-14（万方平台首次上网日期，不代表论文的发表时间）