全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用：99美元
投递稿件

查看量下载量

相关文章

更多...

如何增加人工神经元网络的透明度?*

, PP. 72-84

Keywords: 机器学习,人工神经元网络,先验知识,归纳,演绎,黑箱

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对人工神经元网络应用中最主要的问题之一——“黑箱”特性进行文献综述.增加人工神经元网络系统的透明度是解决该问题必不可少的手段.为了便于理解各种已有方法的应用特点及其局限性，提出“透明度”研究中的方法分类框架.首先将“透明度”研究划分为两种基本策略:1)将先验信息引入系统设计;2)从模型中提取系统相关规则或知识.在此基础上，对各种主要方法进一步分类并进行应用特点介绍.最后对机器学习多目标研究进行讨论.提出基于“性能价格比”与基于提高系统“透明度”的目标函数.指出提高“透明度”是神经元网络研究中最为基本而又直接的解决方案.为此提出“反馈知识增长(KnowledgeIncreasingviaFeedback)”型机器学习方法.

 References

[1]  Waibel A. Modular Construction of TimeDelay Neural Networks for Speech Recognition. Neural Computation, 1989, 1(1): 3946
[2]  Lampinen J, Vehtari A. Bayesian Approach for Neural Networks-Review and Case Studies. Neural Networks, 2001, 14(3): 257274
[3]  Smith S A. A Derivation of Entropy and the Maximum Entropy Criterion in the Context of Decision Problems. IEEE Trans on Systems, Man, and Cybernetics, 1974, 4(1): 157184
[4]  Bernardo J M, Smith A F M. Bayesian Theory. New York, USA: Wiley, 1994
[5]  Lin C T, Lee C S G. NeuralNetworkBased Fuzzy Logic Control and Decision System. IEEE Trans on Computers, 1991, 40(12): 13201336
[6]  Craven M W, Shavlik J W. Visualizing Learning and Computation in Artificial Neural Networks. International Journal on Artificial Intelligence Tools, 1991, 1(3): 399425
[7]  Geng Xin, Zhan Dechuan, Zhou Zhihua. Supervised Nonlinear Dimensionality Reduction for Visualization and Classification. IEEE Trans on Systems, Man, and Cybernetics, 2005, 35(6): 10981107
[8]  Keller T, Gerjets P, Scheiter K, Garsoffky B. Information Visualizations for Knowledge Acquisition: The Impact of Dimensionality and Color Coding. Computers in Human Behavior, 2006, 22(1): 4365
[9]  Yuan Zhuzhi, Chen Zengqiang, Li Xiang. A Survey of Connectionist Intelligent Control. Acta Automatica Sinica, 2002, 28(Supplement): 3859 (in Chinese) (袁著祉, 陈增强,李 翔.联结主义智能控制综述.自动化学报, 2002, 28(增刊): 3859)
[10]  Chen T P, Chen H. Universal Approximation to Nonlinear Operators by Neural Networks with Arbitrary Activation Functions and Its Application to Dynamical Systems. IEEE Trans on Neural Networks, 1995, 6(4): 911917
[11]  Churchland P S, Sejnowski T J. The Computational Brain. Cambridge, USA: MIT Press, 1992
[12]  Yan Pingfan, Huang Duanxu. Artificial Neural Networks-Model Analysis and Application. Hefei, China: Anhui Education Press, 1993 (in Chinese) (阎平凡,黄端旭.人工神经网络——模型,分析与应用.合肥:安徽教育出版社,1993)
[13]  Wang Jue, Shi Chunyi. Discussion on Knowledge Representation. Chinese Journal of Computers, 1995, 18(3): 212224 (in Chinese) (王 珏,石纯一.关于知识表示的讨论.计算机学报, 1995, 18(3): 212224)
[14]  Shi Zhongzhi. Machine Learning. Beijing, China: Tsinghua University Press, 2002(in Chinese) (史忠植.机器学习.北京:清华大学出版社, 2002)
[15]  Duda R O, Hart P E, Stork D. Pattern Classification. 2nd Edition. New York, USA: John Willy, 2001 (Duda R O, Hart P E, Stork D. 模式分类.李宏东,姚天翔,译.北京:机械工业出版社, 2003)
[16]  Haykin S. Neural Networks: A Comprehensive Foundation. 2nd Edition. New York, USA: Printice Hall, 1999 (Haykin S. 神经元网络原理.叶世伟,史忠植,译.北京:机械工业出版社, 2004)
[17]  Mitchell T M. Machine Learning. New York, USA: McGrawHill, 1997 (Mitchell T M. 机器学习.曾华军,张银奎,译.北京:机械工业出版社, 2003)
[18]  Vapnik V. Statistical Learning Theory. New York, USA: John Wiley and Sons, 1998 (Vapnik V. 统计学习理论.许建华,张学工,译.北京:电子工业出版社, 2004)
[19]  AbuMostafa Y S. Learning from Hints in Neural Networks. Journal of Complexity, 1990, 6(2): 192198
[20]  Joerding W H, Meador J L. Encoding a Priori Information in Feedforward Networks. Neural Networks, 1991, 4(6): 847856
[21]  Niyogi P, Girosi F, Poggio T. Incorporating Prior Information in Machine Learning by Creating Virtual Examples. Proc of the IEEE, 1998, 86(11): 21962209
[22]  Scholkopf B, Simard P, Smola A, Vapnik V. Prior Knowledge in Support Vector Kernels // Jordan M I, Kearns M J, Solla S A, eds. Advances in Neural Information Processing Systems 10. Cambridge, USA: MIT Press, 1998: 640646
[23]  Opitz D, Shavlik J. Connectionist Theory Refinement: Genetically Searching the Space of Network Topologies. Journal of Artificial Intelligence Research, 1997, 6(1): 177209
[24]  AbuMostafa Y S. Financial Model Calibration Using Consistency Hints. IEEE Trans on Neural Networks, 2001, 12(4): 791808
[25]  吕柏权,村田纯一,平泽宏太朗.使用三层神经网络的先验信息新学习方法.中国科学E辑, 2004, 34(4): 374390
[26]  Barnard E, Casasent D. Invariance and Neural Nets. IEEE Trans on Neural Networks, 1991, 2(5): 498508
[27]  Poggio T, Girosi T. Networks for Approximation and Learning. Proc of the IEEE, 1990, 78(9): 14811497
[28]  Goutte C, Hansen L K. Regularization with a Pruning Prior. Neural Networks, 1997, 10(6): 10531059
[29]  Hagiwara K. Regularization Learning, Early Stopping and Biased Estimator. Neurocomputing, 2002, 48(1): 937955
[30]  Mallat S. A Wavelet Tour of Signal Processing. New York, USA: Academic Press, 1998 (Mallat S. 信号处理的小波引导.杨力华,戴道清,董文良,湛秋辉,译.北京:机械工业出版社, 2002)
[31]  Xu L. BYY Harmony Learning, Independent State Space, and Generalized APT Financial Analyses. IEEE Trans on Neural Networks, 2001, 12(4): 822849
[32]  Towell G, Shavlik J. KnowledgeBased Artificial Neural Networks. Artificial Intelligence, 1994, 70(1/2): 119165
[33]  Thrun S. Explanation Based Neural Network Learning: A Lifelong Learning Approach. Boston, USA: Kluwer Academic Publisher, 1996
[34]  Psichogios D, Ungar L H. A Hybrid Neural Network-First Principles Approach to Process Modeling. AICHE Journal, 1992, 38(10): 14991511
[35]  CozzioBueler R A. The Design of Neural Networks Using a Priori Knowledge. Ph.D Dissertation. Zurich, Switzerland: Swiss Federal Institute of Technology, 1995
[36]  Huang Deshuang. A Constructive Approach for Finding Arbitrary Roots of Polynomials by Neural Networks. IEEE Trans on Neural Networks, 2004, 15(2): 477491
[37]  Hu B G, Qu H B, Wang Y, Yang S H. A Generalized Constraint Neural Networks Model: Associating Partially Known Relationships for Nonlinear Regressions [EB/OL]. Submitted to IEEE Trans on Neural Networks, 2005[20070202]. http://liama.ia.ac.cn/hubg/paper.html
[38]  Hu Baogang, Ying Hao. Review of Fuzzy PID Control Techniques and Some Important Issues. Acta Automatica Sinica, 2001, 27(4): 374390(in Chinese) (胡包钢,应 浩.模糊PID控制技术研究发展回顾及其面临的若干重要问题.自动化学报, 2001, 27(4): 567584)
[39]  Schapire R E, Rochery M, Rahim M, Gupta N. Boosting with Prior Knowledge for Call Classification. IEEE Trans on Speech and Audio Processing, 2005, 13(2): 174181
[40]  Johansen T A. Identification of NonLinear Systems Using Empirical Data and Prior Knowledge-An Optimization Approach. Automatica, 1996, 32(3): 337356
[41]  Bishop C. Improving the Generalization Properties of Radial Basis Function Neural Networks. Neural Computation, 1991, 3(4): 579588
[42]  Karras D A, Perantonis S J. An Efficient Constrained Training Algorithm for Feedforward Networks. IEEE Trans on Neural Networks, 1995, 6(6): 14201434
[43]  Wilson J A, Zorzetto L F M. A Generalised Approach to Process State Estimation Using Hybrid Artificial Neural Network/Mechanistic Model. Computers and Chemical Engineering, 1997, 21(9): 951963
[44]  Xue Fuzheng, Bai Jie. Nonlinear Modeling and Predictive Control Based on Prior Knowledge and Neural Networks. Journal of System Simulation, 2004, 16(5): 10571059,1063(in Chinese) (薛福珍,柏 洁.基于先验知识和神经网络的非线性建模与预测控制.系统仿真学报, 2004, 16(5): 10571059,1063)
[45]  Sjoberg J, Zhang Q, Ljung L, Benveniste A, Delyon B, Glorennec P Y, Hjalmarsson H, Juditsky A. Nonlinear BlackBox Modeling in System Identification: A Unified Overview. Automatica, 1995, 31(12): 16911724
[46]  Gallant S I. Connectionist Expert Systems. Communications of the ACM, 1988, 31(2): 152169
[47]  Jang J S R. ANFIS: AdaptiveNetworkBased Fuzzy Inference System. IEEE Trans on Systems, Man, and Cybernetics, 1993, 23(3): 665685
[48]  McGarry K, Wermter S, MacIntyre J. Hybrid Neural Systems: from Simple Coupling to Fully Integrated Neural Networks. Neural Computing Surveys, 1999, 2(1): 6293
[49]  Liu B. Theory and Practice of Uncertain Programming. Heidelberg, Germany: PhysicaVerlag, 2002
[50]  Mitra S, Pal S K, Mitra P. Data Mining in Soft Computing Framework: A Survey. IEEE Trans on Neural Networks, 2002, 13(1): 314
[51]  Zhou Zhihua, Chen Shifu. Rule Extraction from Neural Networks. Journal of Computer Research and Development, 2002, 39(4): 398405(in Chinese) (周志华,陈世福.神经网络规则抽取.计算机研究与发展, 2002, 39(4): 398405)
[52]  Zhang Zhaohui, Lu Yuchang, Zhang Bo. Discovering Classification Rules by Using the Neural Networks. Chinese Journal of Computers, 1999, 22(1): 108112(in Chinese) (张朝晖,陆玉昌,张 钹.利用神经网络发现分类规则.计算机学报, 1999, 22(1): 108112)
[53]  Schmitz G P J, Aldrich C, Gouws F S. ANNDT: An Algorithm for Extraction of Decision Trees from Artificial Neural Networks. IEEE Trans on Neural Networks, 1999, 10(6): 13921401
[54]  Buntine W. Graphical Models for Discovering Knowledge // Fayyad U M, PiatetskyShapiro G, Smyth P, Uthurusay R, eds. Advances in Knowledge Discovery and Date Mining. Cambridge, USA: MIT Press, 1995: 5983
[55]  Gevrey M, Dimopoulos I, Lek S. Review and Comparison of Methods to Study the Contribution of Variable in Artificial Neural Network models. Ecological Modeling, 2003, 160(2): 249264
[56]  Tzeng F Y, Ma K L. Opening the Black Box-Data Driven Visualization of Neural Networks // Proc of the IEEE Conference on Visualization. Hangkong, China, 2005: 383390
[57]  Garson G D. Interpreting NeuralNetwork Connection Weights. AI Expert, 1991, 6(4): 4751
[58]  Olden J D, Jackson D A. Illuminating the BlackBox: A Randomization Approach for Understanding Variable Contributions in Artificial Neural Networks. Ecological Modeling, 2002, 154(1): 135150

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133