计算机工程 ›› 2010, Vol. 36 ›› Issue (7): 190-192.doi: 10.3969/j.issn.1000-3428.2010.07.065

• 人工智能及识别技术 • 上一篇    下一篇

感知器学习算法研究

刘建伟,申芳林,罗雄麟   

  1. (中国石油大学(北京)自动化研究所,北京 102249)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2010-04-05 发布日期:2010-04-05

Reserch on Perceptron Learning Algorithm

LIU Jian-wei, SHEN Fang-lin, LUO Xiong-lin   

  1. (Research Institute of Automation, China University of Petroleum, Beijing 102249)
  • Received:1900-01-01 Revised:1900-01-01 Online:2010-04-05 Published:2010-04-05

摘要: 介绍感知器学习算法及其变种,给出各种感知器算法的伪代码,指出各种算法的优点。给出感知器算法在线性可分和线性不可分情况下的误差界定理,讨论各种感知器学习算法的误差界理论,给出各种算法的误差界。介绍感知器学习算法在在线优化场景、强化学习场景和赌博机算法中的应用,并对未解决的问题进行讨论。

关键词: 感知器, 错误界, 赌博机算法, 强化学习

Abstract: This paper introduces some perceptron algorithms and their variations, gives various pseudo-codes, pionts out advantage among algorithms. It gives mistake bound’s theorems of perceptrons algorithm in linearly separable and unlinearly separable situation. It studies their mistake bounds and works out their bounds. It shows their various applications in the online optimization, reinforcement learning and bandit algorithm, and discusses the open problems.

Key words: perceptron, mistake bound, bandit algorithm, reinforcement learning

中图分类号: