Aggarwal Charu C. Artificial Intelligence: A Textbook

Springer, 2021. — 496 p. — ISBN: 978-3-030-72356-9.This textbook covers the broader field of artificial intelligence.The chapters for this textbook span within three categories:Deductive reasoning methods: These methods start with pre-defined hypotheses and reason with them in order to arrive at logically sound conclusions. The underlying methods include search and logic-based methods. These methods are discussed in Chapters 1through 5.Inductive Learning Methods: These methods start with examples and use statistical methods in order to arrive at hypotheses. Examples include regression modeling, support vector machines, neural networks, reinforcement learning, unsupervised learning, and probabilistic graphical models. These methods are discussed in Chapters~6 through 11.Integrating Reasoning and Learning: Chapters~11 and 12 discuss techniques for integrating reasoning and learning. Examples include the use of knowledge graphs and neuro-symbolic artificial intelligence.The primary audience for this textbook are professors and advanced-level students in computer science. It is also possible to use this textbook for the mathematics requirements for an undergraduate data science course. Professionals working in this related field many also find this textbook useful as a reference.An Introduction to Artificial IntelligenceThe Two Schools of Thought
Artificial General Intelligence
The Concept of Agent
Deductive Reasoning in Artificial Intelligence
Inductive Learning in Artificial Intelligence
Biological Evolution in Artificial IntelligenceFurther Reading
Exercises
Searching State SpacesUninformed Search Algorithms
Informed Search: Best-First Search
Local Search with State-Specific Loss Functions
Genetic Algorithms
The Constraint Satisfaction ProblemFurther Reading
Exercises
Multiagent SearchUninformed Search: AND-OR Search Trees
Informed Search Trees with State-Specific Loss Functions
Alpha-Beta Prunin
Monte Carlo Tree Search: The Inductive ViewFurther Reading
Exercises
Propositional LogicPropositional Logic: The Basics
Laws of Propositional Logic
Propositional Logic as a Precursor to Expert Systems
Equivalence of Expressions in Propositional Logic
The Basics of Proofs in Knowledge Bases
The Method of Proof by Contradiction
Efficient Entailment with Definite Clauses.Further Reading
Exercises
First-Order LogicThe Basics of First-Order Logic
Populating a Knowledge Base
Example of Expert System with First-Order Logic
Systematic Inferencing ProceduresFurther Reading
Exercises
Machine Learning: The Inductive ViewLinear Regression
Least-Squares Classificatio
The Support Vector Machine
Logistic Regression
Multiclass Setting
The Naıve Bayes Model
Nearest Neighbor Classifie
Decision Trees
Rule-Based Classifiers
Evaluation of ClassificationFurther Reading
Exercises
Neural NetworksAn Introduction to Computational Graphs
Optimization in Directed Acyclic Graphs
Application: Backpropagation in Neural Networks
A General View of Computational GraphsFurther Reading
Exercises
Domain-Specific Neural ArchitecturesPrinciples Underlying Convolutional Neural Networks
The Basic Structure of a Convolutional Network
Case Studies of Convolutional Architectures
Principles Underlying Recurrent Neural Networks
The Architecture of Recurrent Neural Networks
Long Short-Term Memory (LSTM)
Applications of Domain-Specific ArchitecturesFurther Reading
Exercises
Unsupervised LearningDimensionality Reduction and Matrix Factorization
Clustering
Why Unsupervised Learning Is ImportantFurther Reading
Exercises
Reinforcement LearningStateless Algorithms: Multi-Armed Bandits
Reinforcement Learning Framework
Monte Carlo Sampling
Bootstrapping and Temporal Difference Learning
Policy Gradient Methods
Revisiting Monte Carlo Tree Search
Case Studies
Weaknesses of Reinforcement LearningFurther Reading
Exercises
Probabilistic Graphical ModelsBayesian Networks
Rudimentary Probabilistic Models in Machine Learning
The Boltzmann Machine
Restricted Boltzmann Machines
Applications of Restricted Boltzmann MachinesFurther Reading
Exercises
Knowledge GraphsAn Overview of Knowledge Graphs
How to Construct a Knowledge Graph
Applications of Knowledge GraphsFurther Reading
Exercises
Integrating Reasoning and LearningThe Bias-Variance Trade-Off
A Generic Deductive-Inductive Ensemble
Transfer Learning
Lifelong Machine Learning
An Instructive Example of Lifelong Learning
Neuro-Symbolic Artificial IntelligenceFurther Reading
Exercises