Wallace C.S. — Statistical and Inductive Inference by Minimum Message Length :: Электронная библиотека попечительского совета мехмата МГУ

Главная Ex Libris Книги Журналы Статьи Серии Каталог Wanted Загрузка ХудЛит Справка Поиск по индексам Поиск Форум

Авторизация

Поиск по указателям

Wallace C.S. — Statistical and Inductive Inference by Minimum Message Length

Обсудите книгу на научном форуме

Нашли опечатку?
Выделите ее мышкой и нажмите Ctrl+Enter

Название: Statistical and Inductive Inference by Minimum Message Length

Автор: Wallace C.S.

Аннотация:

Statistical and Inductive Inference by Minimum Message Length will be of special interest to graduate students and researchers in Machine Learning and Data Mining, scientists and analysts in various disciplines wishing to make use of computer techniques for hypothesis discovery, statisticians and econometricians interested in the underlying theory of their discipline, and persons interested in the Philosophy of Science. The book could also be used in a graduate-level course in Machine Learning, Estimation and Model-selection, Econometrics, and Data Mining.

Язык:

Рубрика: Математика/

Статус предметного указателя: Готов указатель с номерами страниц

ed2k: ed2k stats

Год издания: 2005

Количество страниц: 429

Добавлена в каталог: 10.12.2005

Операции: Положить на полку | Скопировать ссылку для форума | Скопировать ID

Предметный указатель

Induction, human      394 396
Induction, MML, practice of      391—399
Induction, of the past      356—365
Induction, of the past, by maximum likelihood      357—358
Induction, of the past, by MML      358—361
Induction, of the past, with deterministic laws      363—365
Inductive conclusions      6
Inductive inference      1—55
Inductive inference, introduction to      5—11
Inductive inference, primitive      387—388
Inductive process      6
Inexplicable present views      362—363
Inference problem, specified      153
Inference(s), Bayesian      see “Bayesian inference”
Inference(s), coding of      148—150
Inference(s), inductive      see “Inductive inference”
Inference(s), Non-Bayesian      28—35
Inference(s), of regular grammars      305—3t4
Inference(s), possible, set of      147—148
Inference(s), statistical      see “Statistical inference”
Infinite entropy distributions      94
Infinite sets, codes for      91—92
Infinite sets, feasible codes for      96 98
information      57—141
Information content of multinomial distribution      81—87
Information matrix, empirical      241
Information, communication of      57—58
Information, defined      57
Information, Fisher      see “Fisher Information”
Information, measurement, of      66—68
Information, pattern and noise, separation of      190—191
Information, Shannon      see “Shannon information”
Information, subjective nature of      79—81
Instructions, Turing machines      101
Integers, optimal codes for      93—96
Invariance, data representation      187—188
Invariance, model representation      188—189
Invariant conjugate priors      52—53 261
Invariants      340
Irregular likelihood functions      242—243
ISO-7, code      61
J-factor model      300—303
Jeffreys prior      48—49 410 412
Joreskog. K.G.      299
Kearns et al. MDL criterion (KMDL)      322 325
Kent. J.T.      300
Kepler's laws      13
KLD (Kullback Leibler distance)      204—205 287—288
KMDL (Kearns et al. MDL criterion)      322 325
Knowledge      5—6
Kolmogorov, A.N.      4 57 102 275 401
Korb. K.B.      323—326 335
Kraft's inequality      65
Kuhn, T.      385
Kullback — Leibler distance (KLD)      204—205 287—288
Langdon, G.G.      73
Large-D message length, MML      237
Latent factor model      297—303
Latent factor model, defining equations for      299
Latent factor model, MML      300—303
Lattice constant      180
Lauguage(s), choice of      132
Lauguage(s), natural      see “Natural languages”
Lauguage(s), scientific      391
leaf nodes      315
Lee, T.C.M.      319
Lengths of explanations      143
Leung Yan Cheong, S.K.      98
Levin search      396—397
Levin, L.A.      392 396 397
Likelihood      30
Likelihood functions, irregular      242—243
Likelihood principle, minimum Message Length approach and      254 255
Likelihood, maximum      see “Maximum likelihood”
Linear regression      270—272
Log likelihood ratio      33 35
Log* code      99 100 409
Loss function      347—348
Loss function, expected value of      189
Machine learning      2
Mansour. Y.      321—325
Mardia. K.V.      300
Marginal maximum likelihood      203—204
Marginal probability      154
Maximum entropy density      90—91
Maximum entropy priors      51—52
Maximum likelihood (ML) method      30
Maximum likelihood estimator      299—300
Maximum likelihood, for Neyman Scott problem      203—204
Maximum likelihood, induction of the past by      357 358
Maximum likelihood, marginal      203—204
Maximum likelihood, normalized (NML)      410—415
Maxwell — Boltzmann statistics      378
MDL (Minimum Description Length) criterion      321—325
MDL (Minimum Description Length) principle      401 408—415
Mealey machine representation      305—307
Mean      27
Mean, discrimination of      193—195
Mean, Normal, with Normal prior, estimation of      173—177
Mean, of multivariate Normal      177—183
Mean, of uniform distribution of known range      183 187
Mean, sample      260
Measurement of information      66—68
Meek, C      327
MEKL      see “Minimum expected K-L distance”
Memories      355 356
Message      59
Message format for mixtures      279—280
Message length formulae, MML      235
Message length, average      234
Message length, curved-prior, MML      236—237
Message length, Dowe's approximation to      209—213
Message length, large-D, MML      237
Message length, small-sample, MML      235—236
Message section      328
Metropolis algorithm      332 333
Micro-state      88
Ming Li      392
Minimal sufficient statistics      163
Minimum Description Length (MDL) criterion      321—325
Minimum Description Length (MDL) Principle      401 408—415
Minimum expected K-L distance (MEKL)      205—208
Minimum expected K-L distance (MEKL), for Neyman — Scott problem      206—208
Minimum Message Length (MML), approach      117—118
Minimum Message Length (MML), as descriptive theory      385—399
Minimum Message Length (MML), binomial example      246—248
Minimum Message Length (MML), coding scheme      222—228
Minimum Message Length (MML), curved-prior message length      236—237
Minimum Message Length (MML), details in specific cases      257—303
Minimum Message Length (MML), efficiency of      230—231
Minimum Message Length (MML), extension to Neyman — Scott problem      252—253
Minimum Message Length (MML), induction of the past by      358—361
Minimum Message Length (MML), large-D message length      237
Minimum Message Length (MML), likelihood principle and      254—255
Minimum Message Length (MML), limitations of      249—250
Minimum Message Length (MML), message length formulae      235
Minimum Message Length (MML), model invariance      229—230
Minimum Message Length (MML), multi-parameter properties of      234—235
Minimum Message Length (MML), multiple latent factors      300—303
Minimum Message Length (MML), multiple parameters in      232—233
Minimum Message Length (MML), negative binomial distribution      253
Minimum Message Length (MML), normal distribution      250—253
Minimum Message Length (MML), practice of induction      391—399
Minimum Message Length (MML), precision of estimate spacing      238—240
Minimum Message Length (MML), properties of estimator      228—240
Minimum Message Length (MML), quadratic approximations to SMML      221—255
Minimum Message Length (MML), quadratic, assumptions of      226—227
Minimum Message Length (MML), related work and      401—415
Minimum Message Length (MML), singularities in priors      237
Minimum Message Length (MML), small-sample message length      235—236

Minimum Message Length (MML), standard formulae      235
Minimum Variance Unbiased estimators      31—32
Minimum-cost estimation      189
Mixture models      275—297
Mixtures, Fisher Information for      290—291
Mixtures, message format for      279—280
ML (Maximum Likelihood) method      30
ML* estimator      299—300
MML      see “Minimum Message Length approach”
Model      28
model classes      408
Model density      177
Model family      28
Model invariance, MML      229—230
Model representation invariance      188—189
Multi-word messages, coding      72—73
Multinomial distributions      247
Multinomial distributions, information content of      81—87
Multinomial distributions, irregularities in      248
Multivariate mean estimator, summary of      183
Multivariate Normal distribution, conjugate priors for      261—264
Multivariate Normal, mean of      177—183
NAT      78
Natural languages, efficiencies of      389—390
Natural languages, hypotheses of      388—390
Natural languages, inefficiencies of      390
Neal, R.      73
Negative binomial distribution      253
Nested union      192
Neyman — Pearson testing      413
Neyman — Scott problem      200—204 218
Neyman — Scott problem, ideal group estimator for      201—202
Neyman — Scott problem, maximum likelihood for      203—204
Neyman — Scott problem, minimum expected K-L distance for      206—208
Neyman — Scott problem, MML extension to      252—253
Neyman — Scott problem, other estimators for      202—203
Ng, A.Y.      321—325
Nit      78
NML (normalized maximum likelihood)      410—415
nodes      61
nodes, children      64
Nodes, dummy      318—319
Noise      190
noise level      273
Non-adiabatic experiment      382—384
Non-Bayesian estimation      30—32
Non-Bayesian inference      28—35
Non-Bayesian model selection      32—35
Non-binary codes      77—78
Non-deterministic laws      344
Non-deterministic laws, deduction with      348—350
Non-random strings      109
Normal density      28
Normal distribution function      29
Normal distribution, conjugate priors for      258—264
Normal distribution, multivariate, conjugate priors for      261—264
Normal distribution, with coarse data      265—266
Normal distribution, with perturbed data      264—265
Normal mean, with Normal prior, estimation of      173—177
Normal prior, estimation of Normal mean with      173—177
Normal, multivariate, mean of      177—183
Normalization      407—408
Normalized maximum likelihood (NML)      410—415
Normalized probability measure      403
Notation, confusion of      144—145
Noun      389
Nuisance parameters      285
Null hypothesis      19 32—33
Observations      8
Occam's razor      1
Oliver, J.J.      268 319
Optimal codes      63—66
Optimal codes, construction of      69—72
Optimal codes, for integers      93—96
Optimal codes, properties of      76—77
Optimum quantizing lattice      178 285
Order      337
Organisms      7 8
Output lape, Turing machines      101
Parameter values      150
Parameters, discrete, imprecise assertion of      284—286
Partial order equivalence      330
Particle-state probability distribution      342
Partitions of hypothesis space      213—215
PAST      368 369
Past disorder, deduction of      345—355
Past, induction of the      see “Induction of the past”
Past, of a computer process      375
Past, regained      369—370
Past, simulation of the      381—382
Patrick, J.D.      275 314—315
Pattern      190
Perturbed data, normal distribution with      264—265
PFSM      see “Probabilistic finite-state machine”
Philosophy of science      1—2
Pipe model      356
Poisson distribution      269—270
Popper. K.      10
Population      150
Possible data, set X of      144—145
Possible inferences, set of      147—148
Posterior      36
Posterior density      37
Posterior distribution      36
Posterior probability      36
Precision approach      216
Precision of estimate spacing      238—240
Predictive distribution      206
Prefix code      01
prefix property      60
PRESENT      368 369
Present views, inexplicable      362—363
Previous likelihood      46
Price, H.      338—339
Primitive inductive inference      387—388
Primitive universal Turing machines (UTM0)      135—140
Prior density      37
Prior distribution      35
Prior estimate probability      270
Prior premises      17
Prior probability      35
Prior probability density      37 150—151
Prior probability density, coding probability arid      222
Priors      35
Priors, alternative      350—353
Priors, conjugate      see “Conjugate priors”
Priors, evolution of      135—141
Priors, invariant conjugate      52—53
Priors, maximum entropy      51—52
Priors, Normal, Normal mean with, estimation of      173—177
Priors, origins of      45—54 133—135
Priors, singularities in      237
Priors, theory description codes as      114 115
Priors, Uniform      182
Priors, uninformative      49—51
Priors, Universal Turing machines as      124—130
Probabilistic finite-state machine (PFSM)      307 314
Probabilistic finite-state machine (PFSM), assertion code for      308—309
Probabilistic model of data      146
Probabilistic regular grammar      308
probability      21—22
Probability density function      25
Probability distributions defined      146
Probability distributions defined, particle-state      342
Probability distributions defined, Turing      103—104
Probability line      74
Probability, coding      149—150
Probability, conditional      21
Punctuated binary codes      92—93
Quantization noise      181

1 2 3

О проекте