book

Artificial Intelligence, 2nd Edition

Name: Artificial Intelligence, 2nd Edition
ISBN: 9781351384384

by Richard E. Neapolitan, Xia Jiang

March 2018

Intermediate to advanced

480 pages

13h 46m

English

Chapman and Hall/CRC

Read now

Unlock full access

Cover
Halftitle
Copyright Page
Table of Contents
Preface
About the Authors
1 Introduction to Artificial Intelligence
1.1 History of Artificial Intelligence1.1.1 What Is Artificial Intelligence?1.1.2 Emergence of AI1.1.3 Cognitive Science and AI1.1.4 Logical Approach to AI1.1.5 Knowledge-Based Systems1.1.6 Probabilistic Approach to AI1.1.7 Evolutionary Computation and Swarm Intelligence1.1.8 Neural Networks& Deep Learning Neural Networks& Deep Learning1.1.9 A Return to Creating HAL1.2 Outline of This Book
PART I Logical Intelligence
2 Propositional logic
2.1 Basics of propositional logic2.1.1 Syntax2.1.2 Semantics2.1.3 Tautologies and logical implication2.1.4 Logical arguments2.1.5 Derivation systems2.2 Resolution2.2.1 Normal forms2.2.2 Derivations using resolution2.2.3 Resolution algorithm2.3 Artificial intelligence applications2.3.1 Knowledge-based systems2.3.2 Wumpus world2.4 Discussion and further reading
3 First-order logic
3.1 Basics of first-order logic3.1.1 Syntax3.1.2 Semantics3.1.3 Validity and Logical Implication3.1.4 Derivation Systems3.1.5 Modus Ponens for First-Order Logic3.2 Artificial Intelligence Applications3.2.1 Wumpus World Revisited3.2.2 Planning3.3 Discussion and Further Reading

4 Certain knowledge representation
4.1 Taxonomic Knowledge4.1.1 Semantic Nets4.1.2 Model of Human Organization of Knowledge4.2 Frames4.2.1 Frame Data Structure4.2.2 Planning a Trip Using Frames4.3 Nonmonotonic Logic4.3.1 Circumscription4.3.2 Default Logic4.3.3 Difficulties4.4 Discussion and Further Reading
5 Learning deterministic models
5.1 Supervised Learning5.2 Regression5.2.1 Simple Linear Regression5.2.2 Multiple Linear Regression5.2.3 Overfitting and Cross Validation5.3 Parameter Estimation5.3.1 Estimating the Parameters for Simple Linear Regression5.3.2 Gradient Descent5.3.3 Logistic Regression and Gradient Descent5.3.4 Stochastic Gradient Descent5.4 Learning a Decision Tree5.4.1 Information Theory5.4.2 Information Gain and the ID3 Algorithm5.4.3 Overfitting
PART II Probabilistic Intelligence
6 Probability
6.1 Probability Basics6.1.1 Probability Spaces6.1.2 Conditional Probability and Independence6.1.3 Bayes’ Theorem6.2 Random Variables6.2.1 Probability Distributions of Random Variables6.2.2 Independence of Random Variables6.3 Meaning of Probability6.3.1 Relative Frequency Approach to Probability6.3.2 Subjective Approach to Probability6.4 Random Variables in Applications6.5 Probability in the Wumpus World
7 Uncertain Knowledge Representation
7.1 Intuitive Introduction to Bayesian Networks7.2 Properties of Bayesian Networks7.2.1 Definition of a Bayesian Network7.2.2 Representation of a Bayesian Network7.3 Causal Networks as Bayesian Networks7.3.1 Causality7.3.2 Causality and the Markov Condition7.3.3 Markov Condition without Causality7.4 Inference in Bayesian Networks7.4.1 Examples of Inference7.4.2 Inference Algorithms and Packages7.4.3 Inference Using Netica7.5 Networks with Continuous Variables7.5.1 Gaussian Bayesian Networks7.5.2 Hybrid Networks7.6 Obtaining the Probabilities7.6.1 Difficulty Inherent in Multiple Parents7.6.2 Basic Noisy OR‐Gate Model7.6.3 Leaky Noisy OR‐Gate Model7.6.4 Further Models7.7 Large-Scale Application: Promedas
8 Advanced Properties of Bayesian Networks
8.1 Entailed Conditional Independencies8.1.1 Examples of Entailed Conditional Independencies8.1.2 d-Separation8.2 Faithfulness8.2.1 Unfaithful Probability Distributions8.2.2 Faithfulness Condition8.3 Markov Equivalence8.4 Markov Blankets and Boundaries
9 Decision Analysis
9.1 Decision Trees9.1.1 Simple Examples9.1.2 Solving More Complex Decision Trees9.2 Influence Diagrams9.2.1 Representing Decision Problems with Influence Diagrams9.2.2 Solving Influence Diagrams9.2.3 Techniques for Solving Influence Diagrams9.2.4 Solving Influence Diagrams Using Netica9.3 Modeling Risk Preferences9.3.1 Exponential Utility Function9.3.2 Assessing r9.4 Analyzing Risk Directly9.4.1 Using the Variance to Measure Risk9.4.2 Risk Profiles9.4.3 Dominance9.5 Good Decision versus Good Outcome9.6 Sensitivity Analysis9.7 Value of Information9.7.1 Expected Value of Perfect Information9.7.2 Expected Value of Imperfect Information
9.8 Discussion and Further Reading
9.8.1 Academics9.8.2 Business and Finance9.8.3 Capital Equipment9.8.4 Computer Games9.8.5 Computer Vision9.8.6 Computer Software9.8.7 Medicine9.8.8 Natural Language Processing9.8.9 Planning9.8.10 Psychology9.8.11 Reliability Analysis9.8.12 Scheduling9.8.13 Speech Recognition9.8.14 Vehicle Control and Malfunction Diagnosis
10 Learning Probabilistic Model Parameters
10.1 Learning a Single Parameter10.1.1 Binomial Random Variables10.1.2 Binomial Random Variables10.2 Learning Parameters in a Bayesian Network10.2.1 Procedure for Learning Parameters10.2.2 Equivalent Sample Size10.3 Learning Parameters with Missing Data⋆
11 Learning Probabilistic Model Structure
11.1 Structure Learning Problem11.2 Score-Based Structure Learning11.2.1 Bayesian Score11.2.2 BIC Score11.2.3 Consistent Scoring Criteria11.2.4 How Many DAGs Must We Score?11.2.5 Using the Learned Network to Do Inference11.2.6 Learning Structure with Missing Data⋆11.2.7 Approximate Structure Learning11.2.8 Model Averaging
11.2.9 Approximate Model Averaging⋆
11.3 Constraint-Based Structure Learning11.3.1 Learning a DAG Faithful to P11.3.2 Learning a DAG in which P Is Embedded Faithfully11.4 Application: MENTOR11.4.1 Developing the Network11.4.2 Validating MENTOR11.5 Software Packages for Learning11.6 Causal Learning11.6.1 Causal Faithfulness Assumption11.6.2 Causal Embedded Faithfulness Assumption11.6.3 Application: College Student Retention Rate11.7 Class Probability Trees11.7.1 Theory of Class Probability Trees11.7.2 Application to Targeted Advertising11.8 Discussion and Further Reading11.8.1 Biology11.8.2 Business and Finance11.8.3 Causal Learning11.8.4 Data Mining11.8.5 Medicine11.8.6 Weather Forecasting
12 Unsupervised learning and reinforcement learning
12.1 Unsupervised learning12.1.1 Clustering12.1.2 Automated discovery12.2 Reinforcement learning12.2.1 Multi‐armed bandit algorithms12.2.2 Dynamic networks⋆12.3 Discussion and further reading
PART III Emergent Intelligence
13 Evolutionary computation
13.1 Genetics review13.2 Genetic algorithms13.2.1 Algorithm13.2.2 Illustrative example13.2.3 Traveling salesperson problem13.3 Genetic programming13.3.1 Illustrative example13.3.2 Artificial ant13.3.3 Application to financial trading13.4 Discussion and further reading
14 Swarm Intelligence
14.1 Ant System14.1.1 Real Ant Colonies14.1.2 Artificial Ants for Solving the TSP14.2 Flocks14.3 Discussion and Further Reading
PART IV Neural Intelligence
15 Neural Networks and Deep Learning
15.1 The Perceptron15.1.1 Learning the Weights for a Perceptron15.1.2 The Perceptron and Logistic Regression15.2 Feedforward Neural Networks15.2.1 Modeling XOR15.2.2 Example with Two Hidden Layers15.2.3 Structure of a Feedforward Neural Network15.3 Activation Functions15.3.1 Output Nodes15.3.2 Output Nodes15.4 Application to Image Recognition15.5 Discussion and Further Reading
PART V Language Understanding
16 Natural Language Understanding
16.1 Parsing16.1.1 Recursive Parser16.1.2 Ambiguity16.1.3 Dynamic Programming Parser16.1.4 Probabilistic Parser16.1.5 Obtaining Probabilities for a PCFG16.1.6 Lexicalized PCFG16.2 Semantic Interpretation16.3 Concept/Knowledge Interpretation16.4 Information Extraction16.4.1 Applications of Information Extraction16.4.2 Architecture for an Information Extraction System16.5 Discussion and Further Reading
References
Index

Content preview from Artificial Intelligence, 2nd Edition

11.2.9 Approximate Model Averaging $⋆$

As is the case for model selection, when the number of possible DAGs is large, we cannot average over all DAGs. In these situations, we heuristically search for high-probability DAGs, and then we average over them. In particular, in the gene expression example, because there are thousands of variables, we could not average over all DAGs. Approximate model averaging is discussed next.

11.2.9.1 Approximate Model Averaging Using MCMC

Next we discuss how we can heuristically search for high-probability structures and then average over them using the Markov Chain Monte Carlo (MCMC) method.

Recall our two examples of model averaging (Examples 11.14 and 11.15). The first involved computing a conditional probability ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Artificial Intelligence For Dummies, 3rd Edition

Publisher Resources

ISBN: 9781351384384

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Artificial Intelligence, 2nd Edition

by Richard E. Neapolitan, Xia Jiang

11.2.9 Approximate Model Averaging $⋆$

11.2.9.1 Approximate Model Averaging Using MCMC

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.