Muutke küpsiste eelistusi

Probabilistic Machine Learning for Civil Engineers [Pehme köide]

4.00/5 (2 hinnangut Goodreads-ist)
(Polytechnique Montréal)
  • Formaat: Paperback / softback, 304 pages, kõrgus x laius x paksus: 254x203x13 mm, 367 color illus.; 734 Illustrations
  • Sari: The MIT Press
  • Ilmumisaeg: 14-Apr-2020
  • Kirjastus: MIT Press
  • ISBN-10: 0262538709
  • ISBN-13: 9780262538701
Teised raamatud teemal:
  • Pehme köide
  • Hind: 64,50 €*
  • * saadame teile pakkumise kasutatud raamatule, mille hind võib erineda kodulehel olevast hinnast
  • See raamat on trükist otsas, kuid me saadame teile pakkumise kasutatud raamatule.
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Lisa soovinimekirja
Probabilistic Machine Learning for Civil EngineersSuurem pilt
  • Formaat: Paperback / softback, 304 pages, kõrgus x laius x paksus: 254x203x13 mm, 367 color illus.; 734 Illustrations
  • Sari: The MIT Press
  • Ilmumisaeg: 14-Apr-2020
  • Kirjastus: MIT Press
  • ISBN-10: 0262538709
  • ISBN-13: 9780262538701
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9780262538701.html
Märksõnad:

An introduction to key concepts and techniques in probabilistic machine learning for civil engineering students and professionals; with many step-by-step examples, illustrations, and exercises.

This book introduces probabilistic machine learning concepts to civil engineering students and professionals, presenting key approaches and techniques in a way that is accessible to readers without a specialized background in statistics or computer science. It presents different methods clearly and directly, through step-by-step examples, illustrations, and exercises. Having mastered the material, readers will be able to understand the more advanced machine learning literature from which this book draws.

The book presents key approaches in the three subfields of probabilistic machine learning: supervised learning, unsupervised learning, and reinforcement learning. It first covers the background knowledge required to understand machine learning, including linear algebra and probability theory. It goes on to present Bayesian estimation, which is behind the formulation of both supervised and unsupervised learning methods, and Markov chain Monte Carlo methods, which enable Bayesian estimation in certain complex cases. The book then covers approaches associated with supervised learning, including regression methods and classification methods, and notions associated with unsupervised learning, including clustering, dimensionality reduction, Bayesian networks, state-space models, and model calibration. Finally, the book introduces fundamental concepts of rational decisions in uncertain contexts and rational decision-making in uncertain and sequential contexts. Building on this, the book describes the basics of reinforcement learning, whereby a virtual agent learns how to make optimal decisions through trial and error while interacting with its environment.



An introduction to key concepts and techniques in probabilistic machine learning for civil engineering students and professionals; with many step-by-step examples, illustrations, and exercises.
List of Figures
xi
List of Algorithms
xix
Acknowledgments xxi
Nomenclature & Abbreviations xxiii
1 Introduction
1(6)
I Background
7(50)
2 Linear Algebra
9(8)
2.1 Notation
9(1)
2.2 Operations
10(2)
2.3 Norms
12(1)
2.4 Transformations
12(5)
2.4.1 Linear Transformations
12(1)
2.4.2 Eigen Decomposition
13(4)
3 Probability Theory
17(18)
3.1 Set Theory
18(1)
3.2 Probability of Events
19(3)
3.3 Random Variables
22(7)
3.3.1 Discrete Random Variables
22(1)
3.3.2 Continuous Random Variables
23(1)
3.3.3 Conditional Probabilities
24(1)
3.3.4 Multivariate Random Variables
25(2)
3.3.5 Moments and Expectation
27(2)
3.4 Functions of Random Variables
29(6)
3.4.1 Linear Functions
30(1)
3.4.2 Linearization of Nonlinear Functions
31(4)
4 Probability Distributions
35(12)
4.1 Normal Distribution
35(6)
4.1.1 Univariate Normal
35(1)
4.1.2 Multivariate Normal
36(1)
4.1.3 Properties
37(3)
4.1.4 Example: Conditional Distributions
40(1)
4.1.5 Example: Sum of Normal Random Variables
40(1)
4.2 Log-Normal Distribution
41(3)
4.2.1 Univariate Log-Normal
41(1)
4.2.2 Multivariate Log-Normal
42(1)
4.2.3 Properties
43(1)
4.3 Beta Distribution
44(3)
5 Convex Optimization
47(10)
5.1 Gradient Ascent
48(2)
5.2 Newton-Raphson
50(2)
5.3 Coordinate Ascent
52(1)
5.4 Numerical Derivatives
53(1)
5.5 Parameter-Space Transformation
54(3)
II Bayesian Estimation
57(48)
6 Learning from Data
59(30)
6.1 Bayes
59(2)
6.2 Discrete State Variables
61(5)
6.2.1 Example: Disease Screening
61(1)
6.2.2 Example: Fire Alarm
62(3)
6.2.3 Example: Post-Earthquake Damage Assessment
65(1)
6.3 Continuous State Variables
66(5)
6.3.1 Likelihood: f(D|x)
66(3)
6.3.2 Evidence: f(D)
69(1)
6.3.3 Posterior: f(x|D)
70(1)
6.3.4 Number of Observations and Identifiability
70(1)
6.4 Parameter Estimation
71(3)
6.4.1 Prior: f(θ)
72(1)
6.4.2 Likelihood: f(V|θ)
73(1)
6.4.3 Posterior PDF: f(θ|D)
73(1)
6.5 Monte Carlo
74(5)
6.5.1 Monte Carlo Integration
74(1)
6.5.2 Monte Carlo Sampling: Continuous State Variables
75(3)
6.5.3 Monte Carlo Sampling: Parameter Estimation
78(1)
6.6 Conjugate Priors
79(3)
6.7 Approximating the Posterior
82(3)
6.7.1 Maximum Likelihood and Posterior Estimates
82(1)
6.7.2 Laplace Approximation
83(2)
6.8 Model Selection
85(4)
7 Markov Chain Monte Carlo
89(16)
7.1 Metropolis
90(2)
7.2 Metropolis-Hastings
92(1)
7.3 Convergence Checks
92(5)
7.3.1 Burn-In Phase
92(1)
7.3.2 Monitoring Convergence
93(1)
7.3.3 Estimated Potential Scale Reduction
94(2)
7.3.4 Acceptance Rate
96(1)
7.3.5 Proposal Tuning
97(1)
7.4 Space Transformation
97(2)
7.5 Computing with MCMC Samples
99(6)
III Supervised Learning
105(50)
8 Regression
107(32)
8.1 Linear Regression
107(8)
8.1.1 Mathematical Formulation
108(2)
8.1.2 Overfitting and Cross-Validation
110(3)
8.1.3 Mathematical Formulation < 1-D
113(1)
8.1.4 Limitations
114(1)
8.2 Gaussian Process Regression
115(11)
8.2.1 Updating a GP Using Exact Observations
116(2)
8.2.2 Updating a GP Using Imperfect Observations
118(1)
8.2.3 Multiple Covariates
119(1)
8.2.4 Parameter Estimation
120(1)
8.2.5 Example: Soil Contamination Characterization
121(1)
8.2.6 Example: Metamodel
122(2)
8.2.7 Advanced Considerations
124(2)
8.3 Neural Networks
126(13)
8.3.1 Feedforward Neural Networks
127(5)
8.3.2 Parameter Estimation and Backpropagation
132(2)
8.3.3 Regularization
134(2)
8.3.4 Example: Metamodel
136(3)
9 Classification
139(16)
9.1 Generative Classifiers
140(4)
9.1.1 Formulation
140(3)
9.1.2 Example: Post-Earthquake Structural Safety Assessment
143(1)
9.2 Logistic Regression
144(2)
9.3 Gaussian Process Classification
146(4)
9.4 Neural Networks
150(2)
9.5 Regression versus Classification
152(3)
IV Unsupervised Learning
155(72)
10 Clustering and Dimension Reduction
157(10)
10.1 Clustering
157(6)
10.1.1 Gaussian Mixture Models
157(5)
10.1.2 K-Means
162(1)
10.2 Principal Component Analysis
163(4)
11 Bayesian Networks
167(14)
11.1 Graphical Models Nomenclature
169(1)
11.2 Conditional Independence
170(1)
11.3 Inference
171(2)
11.4 Conditional Probability Estimation
173(4)
11.4.1 Fully Observed Bayesian Network
173(3)
11.4.2 Partially Observed Bayesian Network
176(1)
11.5 Dynamic Bayesian Network
177(4)
12 State-Space Models
181(32)
12.1 Linear Gaussian State-Space Models
182(12)
12.1.1 Basic Problem Setup
183(3)
12.1.2 General Formulation
186(4)
12.1.3 Forecasting and Smoothing
190(2)
12.1.4 Parameter Estimation
192(1)
12.1.5 Limitations and Practical Considerations
193(1)
12.2 State-Space Models with Regime Switching
194(4)
12.2.1 Switching Kalman Filter
194(3)
12.2.2 Example: Temperature Data with Regime Switch
197(1)
12.3 Linear Model Structures
198(10)
12.3.1 Generic Components
199(4)
12.3.2 Component Assembly
203(2)
12.3.3 Modeling Dependencies Between Observations
205(3)
12.4 Anomaly Detection
208(5)
13 Model Calibration
213(14)
13.1 Least-Squares Model Calibration
215(3)
13.1.1 Illustrative Examples
215(3)
13.1.2 Limitations of Deterministic Model Calibration
218(1)
13.2 Hierarchical Bayesian Estimation
218(9)
13.2.1 Joint Posterior Formulation
218(5)
13.2.2 Predicting at Unobserved Locations
223(4)
V Reinforcement Learning
227(32)
14 Decisions in Uncertain Contexts
229(12)
14.1 Introductory Example
229(1)
14.2 Utility Theory
230(2)
14.2.1 Nomenclature
230(1)
14.2.2 Rational Decisions
231(1)
14.2.3 Axioms of Utility Theory
231(1)
14.3 Utility Functions
232(4)
14.4 Value of Information
236(5)
14.4.1 Value of Perfect Information
236(1)
14.4.2 Value of Imperfect Information
237(4)
15 Sequential Decisions
241(18)
15.1 Markov Decision Process
244(8)
15.1.1 Utility for an Infinite Planning Horizon
245(1)
15.1.2 Value Iteration
246(2)
15.1.3 Policy Iteration
248(3)
15.1.4 Partially Observable Markov Decision Process
251(1)
15.2 Model-Free Reinforcement Learning
252(7)
15.2.1 Temporal Difference Learning
252(2)
15.2.2 Temporal Difference Q-Learning
254(5)
Bibliography 259(8)
Index 267