THE DEVELOPMENT AND FORWORD PROBLEMS
OF NEURAL NETWORK THEORY
LIU Yonghong
(Dept. of Automation, Wuhan University of Technology, Wuhan 430 070)
Abstract This is a survey paper of the development and forwo rd problems of neural network theory. It is divided into four parts: 1. Introduc tion to neural network; 2. The history and present condition; 3. The development trend and forword problems; 4. Conclusions. In the paper, a new comment and vie w for neural network theory is presented.
Key words neural network theory, neural computing, evolutionary computing, study based on neurosciences and mathematics
1 McCulloch W S, Pitts W. A Logical Calculus of the Ideas Immanent in Nervous
Activity, Bulletin of Mathematical Biophysics, 1943, (5):115~133
2 N.维纳著,郝季仁译,控制论,科学出版,1985
3 Von Neumann J. The General and Logical Theory of Automata, Cerebral Mechanisms in
Behavior; The Hixon Sympsium, 1951
4 Turing A M. On Computable Numbers, with an Application to the Entscheidungs
problem, Proc. London Math. Soc., 1936, 2(42):230~265; (43):544~546
5 Turing A M. Systems of Logic Based on Ordinals, Proc. London Math. Soc., 19 39,2
(45):161~228
6 Post E L. Finite Combinatory Process-formulation I, J.Symbolic Logic, 1936,
(1):103~105
7 Hebb D O. The Organization of Behavior, New York:Wiley, 1949
8 Eccles J C. Cholinergic and Inhibitory Synapses in A Pathway from Motor-axon
Collaterals to Motorneurones, J.Physiol., 1954,(126):524
9 Rosenblatt, F., The Perceptron: A Probabilistic Model for Information storage
and Organization in The Brain. Psychological Review, 1958, (65):386~408
10 Widrow B, M E Hoff. Adaptive Switching Circuits. 1960 IRE WESCON con vertion
record: part 4. computers: Man-machine Systems, Los Angeles:96~104
11 Rosenblatt F. Principles of Neurody Namics: Perceptrons and The Theory of Brain
Mechanisms, Spartan, New York, 1962
12 Grossberg S. On the Serial Learning of Lists, Math. Biosci., 1969,(4):201~253
13 Grossberg S. Some Networks that Can Lean, Remenber, and Reproduce any Number of
Compialted Space-time Patterns, Ⅱ, stud. Appl. Math. 1970,(49):135~166
14 Willshaw D J, Buneman O P. Longuest-higgins, H.C Nature 1969,(222):960
15 Nilsson N J. Learning Machines: Foundations of Trainuble Pattern Classifying
Systems, McGraw-hill, New York,1965
16 Holland J H. Genetic Algorithms and the Optimal Allocations of Trials, SIAM
Journal of Computing, 1973,(2):88~105
17 Holland J H. Adaptation in Natural and Artificial Systems, Ann Arbor: The
University of Michigan Press, 1975
18 Stein R B, Leung K V, Mangeron D, Oguztoreli M N. Improved Neuronal Model s for
Studying Neural Networks, Kybernetik, 1974,(15):1~9
19 Heiden U. an der, Existence of Periodic Solutions of a Nerve Equation, Biol .
Cybern., 1976,(21):37~39
20 Grossberg S. Aaptive Pattern Classification and Universal Recoding: Part I :
Parallel Development and Coding of Neural Feature Detectors, Biological Cybern
etics, 1976,(23):121~134
21 Werbos P. Beyond Regression: New Tools for Prediction and Analysis in the
Behavioral Sciences. Ph D Dissertation, Harvard University,1974
22 Fukushima K. Neocognitron: A Self-organizing Multilayered Neural Network.
Biological Cybernetics, 1980,(36):193~202
23 Amari. S-I., Characteristics of Random Nets of Analog Neuron-like Elements ,
IEEE Transactions on Systems, Man and Cybernetics, 1972a, SMC-2:643~657
24 Kohonen T. Automatic formation of Topological Maps in Self-orgnizing Systems:
Proceedings of the 2nd Scandinavian Conf. on Image Analysis, 1981:214~220
25 Kohonen T. Self-organizing formation of Topologically Correct Feature Maps ,
Biol. Cybern. 1982,(43):59~69
26 Kohonen T. Self-organization and Associative Memory. Berlin: Springer-Verlag,
1984
27 Hopfield J J. Neural Networks and Physical Systems with Emergent Collective
Computational Abilities, Proc. Natl. Acad. Sci., USA, 1982,(79):2254~2558
28 Marr D. Vision, San Francisco: W.H.Freeman, 1982
29 Hopfield J J. Neurons with Graded Respone have Collective Computational Pr
operties Like those of Twostate Neurons, Proc. Natl, Acad. Sci., 1984,(81):3088
~3092
30 Hopfield J J, Tank D W. Neural Computation of Decisions in Optimization Prob
lems, Biol. Cybern. 1985,(52):141~152
31 Hopfield J J, Tank D W. Computing with Neural Circuits: A Model, Scien ce, 1986,
(233):625~633
32 Lee Y C. Physica 22D, 1986,86.,276
33 Lapedes A. Physica 22D,1986,247
34 Kirkpatrick S, Gellat Jr C D, Veechi M P. Optimization by Simulated An nealing.
Science, 1983,220(4598):671~681
35 Hinton G E, Sejuowski T J, Ackley D H. Boltzmann Machiues: Cotraint Satisfaction
Networks that Learn, Carnegie-Mellon University, Tech, Report CMU-CS -84-119,
1984
36 Ackley D, Hinton G, Sejnowski T. A Learning Algorithm for Boltzmann machines.
Cognitive Science, 1985,(9):147~169
37 Sejnowski T. Higher Order Boltzmann Machines. In: Denker J ed. AIP Conf
Prpoceeding 151:Neural Networks for Comptuing, New Youk: American Institute of
Phys ics, 1986,398~403
38 Poggio T, et al. An analog model of Computation for Ill-posed Problems of Early
Vision. Artif Intell Lab Memo, 783,MIT, 1984
39 Poggio T, et al. Computational Vision and Regularization Theory. Neture (Lond),
1985,(3):314~319
40 Hecht-Nielsen, R., The Theory of Backpropagation Neural Network, In Review, 1988
41 钱学森 (主编), 关于思维科学,上海人民出版社,1986
42 姚国正,汪云九,神经网络的集合运算,信息与控制,1989,18(2):31 ~40
43 斯华龄[美],电脑人脑化:神经网络—第六代计算机(普及本),北京大学出版社,19 92
44 Chua L O, Yang L. Cellular Neural Networks: Theory. IEEE Transactions on
Circuits and Systems, 1988,(35):1257~1272
45 Chua L O, Yang L. Cellular Neural Networks: Application, IEEE Transactions on
Circuits and Systems 1988, (35):1273~1290
46 Kosko B. Adaptive Bidirectional Associative Memories, Appl. Opt., 1987,26
(23):4947~4860
47 Kosko B. Constructing an Associative Memory, Byte, 1987,12(10):1 37~144
48 Kosko B. Bidirectional Associative Memories, IEEE Trans. on Man, Systems and
Cybernitics, 1988,(18):49~59
49 Muhlenbein H. Parallel Genetic Algorithms, Population Genetics and Combina
torial Optimization, in J.D.Schaffer, Ed. Proceedings of the Third International
Conference on Genetic Algorithms (ICGA), 1989,416~421
50 Muhlenbein H. Limitations of Multi-layer Perceptron Networks-steps Towards
Genetic Neural Networks, Parallel Computing, 1990,(14):249~260
51 Aleksander I. The Logic of Connectionist Systems, Neural Computing Archite
ctures, MIT Press, 1989
52 廖晓昕. 细胞神经网络的数学理论(Ⅰ)、(Ⅱ),中国科学(A辑),1994,24 (9):902~910;
24(10):1037~1046
53 Jenkins B K, A R Tanguay. Jr. Optical Architectures for Neural Network
Implementation, Handbook of Neural Computing and Neural Networks, MIT Press,
Bosto n, 1995:673~677
54 McAulay A D, Wang J, Ma C. Optical Heteroassociative Memory Using Spatial Light
Rebroadcasters. Appl, Opt., 1990,29(14):2067~2073
55 Jewel J L, Lee Y H, Scherer A, et al. Surface Emitting Microlasers for Photonic
Switching and Interclip Connection. Opt. Eng., 1990,29(3):2 10~214
56 阮昊,陈述春,戴凤妹,千福熹. 利用电子俘获材料实现光学IPA神经网络模型,光学学报,
1997,17(6):766~771
57 申金媛,常胜江,张延火斤,母国光. 基于联想存储级 联WTA模型的旋转不变识别,光学学
报,1997,17(10):1352~1356
58 吴佑寿,赵明生,丁晓青. 一种激励函数可调的新人工神经网络及应用,中国科学(E辑),
1997,27(1):55~60
59 郝红卫,戴汝为. 集成手写汉字识别方法与系统,中国科学(E辑), 1997,27(16):556~
559
60 Narendra K, Parthasarathy K. Identification and Control of Dynamical Systems
Using Neural Networks. IEEE Trans on Neural Networks, Mar.1990,1(1):4~27
61 戴先中,刘军,冯纯伯. 连续非线性系统的神经网络α阶逆系统控制方法,自动化学报 ,
1998,24(4):463~468
62 Miller W T. Real-time Application of Neural Networks for Sensor-based Control
of Robots. with Vision, IEEE, Trans. Syst., Man, Cybern., 1989,(19):825~831
63 Miller T W, et al. (Eds), Neural Networks for Control, Cambridge, MA, MIT Press,
1990
64 Lane S H, et al. Theory and Development of Higher Order CMAC Neural Ne tworks,
in Special Issue on Neural Networks in Control Systems, (Antsaklis, P.J. ,Ed.),
IEEE Control Systems Magazine 1992,12(2):23~30
65 Bnlsari A. Some Analytical Solutions to the General Approximation Problem for
Feedforward Neural Networks. Neural Networks 1993,(6):991~996
66 朱文革. 广义小波变换及其在人工神经网络中的应用,应用数学学报,1997,20 (2)
67 罗忠,谢永斌,朱重光. CMAC学习过程收敛性研究,自动化学报,1997,23(4):455~461
68 蔚承建,姚更生更生,何振 亚. 改进的进化计算及其应用,自动化学报,1998,24(2):
262~265
69 张讲社,徐宗本,梁怡. 整体退火遗传算法及其收敛充要条件,中国科学(E辑),1997 ,
27(2):154~164
70 Hertz J, et al. Introduction to Theory of Neural Compution. Sant Fee Complexity
Science Series, 1991:156
71 Anthony M, Biggs N. Computational Learning Theory. Combridge University Press,
1992
72 阎平凡. 人工神经网络的容量、学习与计算复杂性,电子学报,1995,23 (4):63~67
73 钟义信,杨义先. 中国神经网络首届学术大会论文集,北京,1990
74 焦李成. 神经网络计算,西安电子科技大学出版社,1993
75 史忠植. 神经计算,电子工业出版社,1993作者: 小大小 时间: 07-1-22 22:16
提示: 作者被禁止或删除 内容自动屏蔽作者: lwf_2020 时间: 07-6-5 12:23
提示: 作者被禁止或删除 内容自动屏蔽