Zum Hauptinhalt springen

On the learning of discrete probability distributions : 確率分布の学習に関する研究

Hicks, Craig ; Hicks, Craig [著]
1996
Online Hochschulschrift

Titel:
On the learning of discrete probability distributions : 確率分布の学習に関する研究
Autor/in / Beteiligte Person: Hicks, Craig ; Hicks, Craig [著]
Link:
Veröffentlichung: 1996
Medientyp: Hochschulschrift
Sonstiges:
  • Nachgewiesen in: National Diet Library Digital Collections - 国立国会図書館デジタルコレクション
  • Contents Note: 論文目録 / p1 (0001.jp2) -- Contents / p2 (0005.jp2) -- Acknowledgements / p1 (0004.jp2) -- 1 Introduction / p1 (0011.jp2) -- 1.1 The objectives of this reseach / p1 (0011.jp2) -- 1.2 Practical techniques for improving generalization ability in input/output function estimation / p2 (0012.jp2) -- 1.3 The bias/variance dilemma / p4 (0014.jp2) -- 1.4 Some other approaches to generalization / p5 (0015.jp2) -- 1.5 A discussion of pf estimation / p6 (0016.jp2) -- 1.6 Boltzmann model and Boltzmann machine / p8 (0018.jp2) -- 1.7 Issues in applying complexity based generalization to pf estimation / p10 (0020.jp2) -- 1.8 Outline of this thesis / p11 (0021.jp2) -- 2 Notation / p13 (0023.jp2) -- 3 A framework for complexity and generalization / p15 (0025.jp2) -- 3.1 Introduction / p15 (0025.jp2) -- 3.2 The framework / p16 (0026.jp2) -- 3.3 Relation to bias and variance / p23 (0033.jp2) -- 3.4 Conclusions / p24 (0034.jp2) -- 4 Probability function(pf)estimation / p26 (0036.jp2) -- 4.1 Introduction / p26 (0036.jp2) -- 4.2 A random variable and its probability function / p26 (0036.jp2) -- 4.3 Modeling / p27 (0037.jp2) -- 4.4 Training data and empirical pf / p28 (0038.jp2) -- 4.5 Sampling pf / p28 (0038.jp2) -- 4.6 Estimation / p29 (0039.jp2) -- 4.7 Fisher information matrix and its relation to dispersion covariance / p30 (0040.jp2) -- 4.8 Sufficient statistics and variances in different coordinate systems / p31 (0041.jp2) -- 4.9 Efficiency / p33 (0043.jp2) -- 4.10 Entropy,cross-entropy,and divergence / p33 (0043.jp2) -- 4.11 Metrics for pf estimation / p34 (0044.jp2) -- 4.12 A special example: The maximum likelihood estimator applied to a multinomial distribution / p34 (0044.jp2) -- 5 Optimal complexity parameter / p37 (0047.jp2) -- 5.1 Introduction / p37 (0047.jp2) -- 5.2 Preliminary definitions and review / p37 (0047.jp2) -- 5.3 Optimal complexity parameter / p43 (0053.jp2) -- 5.4 Conclusions / p48 (0058.jp2) -- 6 Information theoretic and geometric interpretations of learning in a BM / p50 (0060.jp2) -- 6.1 Introduction / p50 (0060.jp2) -- 6.2 A General Boltzmann machine / p52 (0062.jp2) -- 6.3 A Geometric Approach / p54 (0064.jp2) -- 6.4 Information theoretic and geometric characterizations of learning / p57 (0067.jp2) -- 6.5 Conclusions / p63 (0073.jp2) -- 7 The maximum sampling likelihood estimate(MSLE)for a multinomial distribution / p66 (0076.jp2) -- 7.1 Introduction / p66 (0076.jp2) -- 7.2 Definitions and review / p68 (0078.jp2) -- 7.3 Maximum likelihood estimator(MLE)and its efficieny for a multinomial model set / p77 (0087.jp2) -- 7.4 Maximum sampling likelihood estimator(MSLE) / p79 (0089.jp2) -- 7.5 The MSLE applied to other statistical models / p81 (0091.jp2) -- 7.6 An analytic solution to the MSLE for a multinomial model / p81 (0091.jp2) -- 7.7 Example:Binomial distribution / p82 (0092.jp2) -- 7.8 Discussion / p85 (0095.jp2) -- 7.9 Conclusions / p87 (0097.jp2) -- 8 Conclusions / p89 (0099.jp2) -- A Appendix for Chapter5 / p92 (0102.jp2) -- B Appendix for Chapter6 / p95 (0105.jp2) -- B.1 Definitions and lemmas for proofs in Appendix B.2 / p95 (0105.jp2) -- B.2 Proofs for theorems and corollaries in Chapter6 / p98 (0108.jp2) -- C Appendix for Chapter7 / p102 (0112.jp2) -- Bibliography / p107 (0117.jp2)
  • Document Type: 博士論文
  • Rights: 国立国会図書館/図書館・個人送信限定
  • Notes: 博士論文

Klicken Sie ein Format an und speichern Sie dann die Daten oder geben Sie eine Empfänger-Adresse ein und lassen Sie sich per Email zusenden.

oder
oder

Wählen Sie das für Sie passende Zitationsformat und kopieren Sie es dann in die Zwischenablage, lassen es sich per Mail zusenden oder speichern es als PDF-Datei.

oder
oder

Bitte prüfen Sie, ob die Zitation formal korrekt ist, bevor Sie sie in einer Arbeit verwenden. Benutzen Sie gegebenenfalls den "Exportieren"-Dialog, wenn Sie ein Literaturverwaltungsprogramm verwenden und die Zitat-Angaben selbst formatieren wollen.

xs 0 - 576
sm 576 - 768
md 768 - 992
lg 992 - 1200
xl 1200 - 1366
xxl 1366 -