Causality, Correlation and Artificial Intelligence for Rational Decision Making

Marwala Tshilidzi. Causality, Correlation and Artificial Intelligence for Rational Decision Making (WSPC,2015)(ISBN 9789814630863)(600dpi)(204p) ......Page 3
Copyright ......Page 4
Contents ix ......Page 7
Preface v ......Page 5
Acknowledgments vii ......Page 6
1.1 Introduction 1 ......Page 12
1.2.2 Correlation function 2 ......Page 13
1.3.2 Theories of causality 4 ......Page 15
1.3.3 What is a causal function? 10 ......Page 21
1.4.1 Neural networks 11 ......Page 22
1.4.2 Hopfield networks 12 ......Page 23
1.4.4 Particle swarm optimization 13 ......Page 24
1.5 Rational Decision Making 14 ......Page 25
1.6 Summary and Outline of the Book 15 ......Page 26
References 16 ......Page 27
2.1 Introduction 23 ......Page 34
2.2.1 Auto-associative memory network 24 ......Page 35
2.2.2 Principal component analysis 26 ......Page 37
2.2.3 Expectation maximization algorithm 28 ......Page 39
2.3 Genetic Algorithm 32 ......Page 43
2.3.2 Crossover 33 ......Page 44
2.3.4 Reproduction 34 ......Page 45
2.4 Multi-layer Perceptron 35 ......Page 46
2.5 Experimental Comparison 36 ......Page 47
References 38 ......Page 49
3.1 Introduction 43 ......Page 54
3.2 Induction, Deduction, and Abduction 44 ......Page 55
3.3 What is Causality? 45 ......Page 56
3.4 Multi-layer Perceptron Causal Machine 47 ......Page 58
3.4.1 The architecture of the MLP causal machine 48 ......Page 59
3.4.2 Interstate conflict 50 ......Page 61
3.5.1 Theoretical foundation 51 ......Page 62
3.5.2 Applications to condition monitoring 54 ......Page 65
3.6.1 Theoretical foundation 55 ......Page 66
3.6.2 Application to a steam generator 58 ......Page 69
References 59 ......Page 70
4.1 Introduction 65 ......Page 76
4.2 Multi-layer Perceptron Neural Network 66 ......Page 77
4.4 Genetic Algorithms 67 ......Page 78
4.4.2 Crossover 68 ......Page 79
4.4.4 Reproduction 69 ......Page 80
4.5 Particle Swarm Optimization 70 ......Page 81
4.6 Simulated Annealing 73 ......Page 84
4.6.3 Monte Carlo method 75 ......Page 86
4.6.5 Acceptance probability function: Metropolis algorithm 76 ......Page 87
4.7 Missing Data Estimation: Case Studies 77 ......Page 88
4.7.1 Mechanical system 78 ......Page 89
4.8 Conclusions 79 ......Page 90
References 80 ......Page 91
5.1 Introduction 87 ......Page 98
5.2 Granger Causality 88 ......Page 99
5.3 Multi-layer Perceptron for Granger Causality 89 ......Page 100
5.3.1 Bayesian statistics 90 ......Page 101
5.3.2 Hybrid Monte Carlo (HMC) 91 ......Page 102
5.4 RBF for Granger Causality 94 ......Page 105
5.4.2 Pseudo-inverse methods 96 ......Page 107
5.5 Example: Mackey-Glass System 97 ......Page 108
References 99 ......Page 110
6.1 Introduction 105 ......Page 116
6.2 Neyman-Rubin Causal Model 106 ......Page 117
6.2.1 Missing data mechanism 107 ......Page 118
6.2.2 Missing data imputation methods 108 ......Page 119
6.3.1 Directed acyclic graph 109 ......Page 120
6.3.2 Associations between variables 110 ......Page 121
6.3.3 d-separation 112 ......Page 123
6.3.4 Back-door adjustment 113 ......Page 124
6.3.5 Front-door adjustment 114 ......Page 125
6.3.6 Rules for do-calculus 115 ......Page 126
6.3.7 Pearl inferred causation algorithm 116 ......Page 127
6.3.8 Examples of using do-calculus 117 ......Page 128
6.4 Granger Causality 118 ......Page 129
6.5 Comparison: Neyman-Rubin, Pearl and Granger Causality  119 ......Page 130
References 120 ......Page 131
7.1 Introduction 125 ......Page 136
7.2 Causal Machine to Granger Causality 126 ......Page 137
7.2.1 Multi-layer perceptron 128 ......Page 139
7.2.2 Scaled conjugate gradient method 129 ......Page 140
7.3.1 Auto-associative network for missing data estimation 131 ......Page 142
7.3.2 Nelder-Mead simplex optimization method 132 ......Page 143
7.3.3 Granger causality 135 ......Page 146
7.4 Automatic Relevance Determination for Granger Causality 136 ......Page 147
7.5 Experimental Investigation: Mackey-Glass Time-Delay Differential Equation 139 ......Page 150
References 141 ......Page 152
8.1 Introduction 147 ......Page 158
8.3 Rational Decision Making Process 149 ......Page 160
8.4 Bounded-Rational Decision Making 150 ......Page 161
8.5 Flexibly-bounded Rational Decision Making 152 ......Page 163
8.5.1 Advanced information processing 154 ......Page 165
8.5.3 Intelligent machines 156 ......Page 167
8.6.1 Condition monitoring 157 ......Page 168
8.6.2 HIV modeling 159 ......Page 170
8.7 Conclusions 160 ......Page 171
References 161 ......Page 172
9.1 Introduction 167 ......Page 178
9.2 Rational Decision Making 168 ......Page 179
9.3 What is Irrationality? 170 ......Page 181
9.5 Irrational Decision Making and the Theory of Marginalization of Irrationality in Decision Making 173 ......Page 183
9.6 Application of the Marginalization of Irrationality Theory for Breast Cancer Diagnosis 175 ......Page 186
9.6.1 MLP 176 ......Page 187
9.6.2 RBF 178 ......Page 189
9.6.3 Auto-associative neural network based on the MLP  179 ......Page 190
9.6.4 Auto-associative network based on the RBF 180 ......Page 191
References 182 ......Page 193
10.1 Introduction 187 ......Page 198
10.2 Way Forward 188 ......Page 199
References 189 ......Page 200
Index 191 ......Page 202
cover......Page 1