摘要
信息几何是九十年代初开始形成的理论，它将流形上的现代微分几何方法引入到计算神经科学中，为神经网络和信息论提供了十分有用的新的数学工具，也为大脑信息传输方式引入新的观念。近年，信息几何在Ｂｏｌｔｚｍａｎｎ机、神经网络的学习方法、隐单元模型理论、统计推断及序列分析诸方面产生了成功的应用。理论的发展与丰富的应用显示出几何学方法在神经科学与信息科学中具有强大的作用。
出处
《生物物理学报》
CAS
CSCD
北大核心
1999年第2期243-248,共6页
Acta Biophysica Sinica
参考文献1
-
1Rao C R，Bull Calcutta Math Soc，1945年，37卷，81页
同被引文献17
-
1Amari S. Differential-Geometrical Methods in Statistics: Lecture Notes in Statistics. New York: Springer, 1985
-
2Azam F. Biologically Inspired Modular Neural Networks. Ph. D Dissertation. Virginia Polytechnic Institute and State University,2000. http://scholar.lib.yr.edu/theses/available/etd-06092000-12150028/unrestricted/etd.pdf
-
3Dayan P, et al. The Helmholtz Machine. Neural Computations, 1995, 7:889-904
-
4Xu L. A Unified Learning Scheme: Bayesian-Kullback Ying-Yang Maching Advances in Neural Information Processing Systems, 1996, 8:444-450
-
5Arnari S. Information Geometry of the EM and EM Algorithms for Neural Networks, Neural Networks, 1995, 8(9) : 1379 - 1408
-
6Amari S. Information Geometry of Neural Networks-New Bayesian Duality Theory. In: Proc of the International Conference on Neural Information Processing. Hong Kong, 1996, 3 - 6
-
7fgG Bebis, M Georgiopoulos. Feed-forward neural networks:Why network size is so important [J]. IEEE Potentials, 1994,13(4) : 27-31
-
8T Kavzaglu. Determining optimum structure for artificial neural networks [C] . The 24th Annual Technical Conf and Exhibition of the Remote Sensing Society, Cardiff, UK, 1999
-
9S E Fahlman, C Lebiere. The cascade-correlation learning architecture [G]. In: Advances in Neural Information Processing Systems. San Francisco: Morgan Kaufmann, 1990.524-532
-
10J Sietsma, R J Dow. Neural net pruning-Why and how [C].IEEE Int'l Conf on Neural Networks, San Diego, 1988
引证文献2
-
1刘蕴辉,罗四维,李爱军,黄华.神经网络的层次化学习机制探讨[J].模式识别与人工智能,2004,17(3):332-336.
-
2刘蕴辉,罗四维,黄华,李爱军.修剪算法的信息几何分析[J].计算机研究与发展,2006,43(9):1609-1614.
-
1黄燕萍.几何光学成像的概念、计算和应用前景[J].物理教学,2011(4):9-12.
-
2顾凡及.计算神经科学[J].科学,1995,47(6):11-14. 被引量：1
-
3拉巴次仁.非线性系统问题的几何学方法探析[J].西藏大学学报（社会科学版）,2008,23(6):107-108.
-
4向绪言,刘丽芳.EM方法的一种修正及应用[J].湖南文理学院学报（自然科学版）,2010,22(4):3-6.
-
5严酷的魔王.目标,沙漠里的狮子,行动![J].初中生学习（高）,2012(4):8-8.
-
6李富斌.含碎裂机制的广义凝结方程的几何学表述[J].高能物理与核物理,1992,16(9):790-793.
-
7邱仲潘.通往朗兰兹纲领之路[J].自然与科技,2012(3):58-59.
-
8汪云九,唐孝威,吴建永,周昌乐.意识的计算神经科学研究[J].科学通报,2001,46(13):1140-1144. 被引量：6
-
9T.J.Sejnowski,C.Koch,P.S.Churchland,潘泓.计算神经科学[J].世界科学,1989,11(7):5-8.
-
10Jieqiong WU Shengjia LI.STABILIZATION OF WAVE EQUATION WITH VARIABLE COEFFICIENTS BY NONLINEAR BOUNDARY FEEDBACK[J].Journal of Systems Science & Complexity,2011,24(5):875-882. 被引量：3
