An autonomous system with inner modeled associative memory
An autonomous system with inner modeled associative memory
批准号:
13450176
负责人:
OBAYASHI Masanao
金额:
$4.16万
依托单位:
依托单位国家:
日本
项目类别:
Grant-in-Aid for Scientific Research (B)
财政年份:
2001
资助国家:
日本
项目状态:
已结题
起止时间:
2001 至 2003
中文摘要
实现具有内模联想记忆的自治系统,对于研究人脑的功能和生物的学习方法具有重要意义。在这些考虑下,我们主要开发了i)对于强化学习,一种非对称概率密度函数的快速学习方法,以有效地实现试错法ii)对于强化学习,一种引入时变参数思想的学习方法,以适应快速变化的动态环境iii)具有函数型突触权重的混沌神经网络,在每个存储的模式彼此具有强相关性的情况下,其使得能够比常规更容易地检索存储的模式。一种时间序列数据的检索方法,特别是对于具有相同的第一个数据但之后不同的多个时间序列数据,v)引入混沌边缘的思想的鲁棒混沌控制方法,即系统处于混沌状态和非混沌状态之间的状态vi)通过引入随机上升梯度强化学习方法作为混沌时间序列的预测方法,提高了混沌时间序列的预测精度。通过模拟研究澄清
英文摘要
To realize the autonomous system with inner modeled associative memory, it is very useful to research the function of the human brain and learning method of the living things. Under these considerations, we mainly developedi) for reinforcement learning, a faster learning method with asymmetric probability density function to realize trial and error effectivelyii) for reinforcement learning, a learning method introducing the idea of time-varying parameters in order to adapt to dynamical environments which change rapidlyiii) chaotic neural networks with function typed synaptic weights which enable easier retrieval of stored patterns than conventional in the case that each stored patterns have strong correlation each otheriv) a retrieval method for time-series data, particularly for plural time-series data which have same first data but different after thatv) robust chaotic control method introducing the idea of edge of chaos that the system is in the state between chaotic state and non-chaotic statevi) high precision of chaotic time series prediction by introducing the stochastic ascent gradient reinforcement learning method as prediction methodThese validity has been clarified by simulation studies
期刊论文(66)
专著(0)
科研奖励(0)
会议论文
登录
查看更多内容
M.Obayashi: "Associative Memory and Mutual Information In a Chaotic Neural Network Introducing Function Typed Synaptic Weights"Transactions of Institute of Electrical Engineers of Japan. Vol.123, No.9. 1631-1637 (2003)
M.Obayashi:“引入函数类型突触权重的混沌神经网络中的联想记忆和互信息”日本电气工程师学会汇刊。
DOI:
--
发表时间:
期刊:
影响因子:
--
作者:
[]
通讯作者:
K.Kobayashi: "A chaotic memory search model based on associative dynamics using features in stored patterns"Proc.of 41^<st> Society of Instrument and Control Engineering Annual Conference. 2919-2924 (2002)
K.Kobayashi:“使用存储模式中的特征,基于关联动力学的混沌记忆搜索模型”Proc.of 41^<st> 仪器与控制工程学会年会。
DOI:
--
发表时间:
期刊:
影响因子:
--
作者:
[]
通讯作者:
大林正直, 夕田憲治, 大宮理恵, 小林邦和: "開放型記憶行列を持つカオスニューラルネット連想記憶システムと相互情報量"電気学会論文誌C. 123・9. 1631-1637 (2003)
Masanao Obayashi、Kenji Yuta、Rie Omiya、Kunikazu Kobayashi:“具有开放记忆矩阵和互信息的混沌神经网络联想记忆系统”日本电气工程师学会会刊 C. 123・9 (2003)。
DOI:
--
发表时间:
期刊:
影响因子:
--
作者:
[]
通讯作者:
K.Umesako, M.Obayashi, K.Kobayashi: "Evolutionary and time-varying reinforcement learning system based on overlap of rules"Proc.of 6th Japan-France Congress on Mechatronics and 4^<th> Asia-Europe Congress on Mechatronics (JFM2003). 202-207 (2003)
K.Umesako,M.Obayashi,K.Kobayashi:“基于规则重叠的进化和时变强化学习系统”第6届日法机电一体化大会和第4届亚欧机电一体化大会的Proc.(
DOI:
--
发表时间:
期刊:
影响因子:
--
作者:
[]
通讯作者:
梅迫公輔, 大林正直, 小林邦和: "時変パラメータを持つ進化的強化学習システム"電気学会論文誌C. 124・7. (2004)
Kosuke Umesako、Masanao Obayashi、Kunikazu Kobayashi:“具有时变参数的进化强化学习系统”,日本电气工程师学会汇刊 C. 124, 7. (2004)
DOI:
--
发表时间:
期刊:
影响因子:
--
作者:
[]
通讯作者:
共 33 条
Development of a brain information processing imitation based autonomous behavior model with amygdala model
-
批准号:25330287
-
项目类别:Grant-in-Aid for Scientific Research (C)
-
资助金额:$3.16万
-
财政年份:2013
-
负责人:OBAYASHI Masanao
-
依托单位:
A Mathematical Model of the Olfactory System Considering Cooperation with Memory System of the Brain and Learning Theory and Its Application
-
批准号:20500277
-
项目类别:Grant-in-Aid for Scientific Research (C)
-
资助金额:$2.75万
-
财政年份:2008
-
负责人:OBAYASHI Masanao
-
依托单位:
Modeling and control of nonlinear complex system by fusion of control theory and learning network
-
批准号:10650433
-
项目类别:Grant-in-Aid for Scientific Research (C)
-
资助金额:$1.73万
-
财政年份:1998
-
负责人:OBAYASHI Masanao
-
依托单位:
海外基金