book

Artificial Intelligence: Beyond Classical AI

Name: Artificial Intelligence: Beyond Classical AI
Author: Reema Thareja
ISBN: 9789357053778

by Reema Thareja

April 2024

Intermediate to advanced

632 pages

17h 38m

English

Pearson India

Read now

Unlock full access

Cover
About Pearson
Title Page
Contents
Preface
About the Book
Acknowledgments
About the Author
1. Introduction to Artificial Intelligence
1.1 What is Artificial Intelligence?1.1.1 How Does AI Work?1.1.2 Advantages and Disadvantages of Artificial Intelligence1.2 History of Artificial Intelligence1.3 Types of Artificial Intelligence1.3.1 Weak AI1.3.2 Strong AI1.3.3 Reactive Machines1.3.4 Limited Memory1.3.5 Theory of Mind1.3.6 Self-Awareness1.4 Is Artificial Intelligence Same as Augmented Intelligence and Cognitive Computing?1.5 Machine Learning and Deep Learning1.6 Applications of AI1.7 Robotics—an Application of AI1.7.1 Types of Robots1.7.2 Uses of Robotics1.8 Drones Using AI1.9 The Future of AI1.10 No Code AI1.10.1 Why No-Code AI?1.10.2 Future of No Code AI1.10.3 Why No-Code AI Must be Used?1.11 Low Code AI1.11.1 Low-Code vs No-Code AI Development1.11.2 Who Uses Low-Code Development?1.11.3 Low-Code AI Platform for Computer Vision1.11.4 Components of Low-Code AI Platforms1.11.5 Disadvantages of Low-Code/No-Code Platforms1.11.6 Is Low-Code the Future of Software Development?Programmer’s ZoneKey TermsRecapitulation PointsAnswer the QuestionsFill UpState True or FalseMultiple Choice QuestionsFind Out Three AI Tools forApplication Based QuestionsLinks to ExploreAnswers
2. Artificial Intelligence Technologies
2.1 Techniques in AI2.2 Machine Learning Model2.2.1 Types of Machine Learning Algorithms2.3 Regression Analysis in Machine Learning2.3.1 How Regression Analysis Works?2.3.2 Model Evaluation Metrics2.3.3 Types of Regression2.4 Classification Techniques2.4.1 K-Nearest Algorithm2.4.2 Decision Trees2.4.3 Random Forests2.5 Clustering Techniques2.5.1 Overview of Clustering Techniques2.5.2 K-Means Algorithm2.5.3 Applications of Clustering in Real-World Scenarios2.5.4 Evaluation Metrics for Clustering2.5.5 How K-Means Algorithm Works?2.5.6 Pros and Cons of K-Means Algorithm2.5.7 Density-Based Spatial Clustering of Applications with Noise (Dbscan)2.6 Naïve Bayes Classification2.6.1 Understanding Conditional Probability2.6.2 The Bayes Rule2.6.3 Types of Events2.6.4 Naive Bayes Algorithm2.6.5 Laplace Correction2.6.6 Pros and Cons of Naive Bayes Algorithm2.6.7 Applications2.7 Neural Network2.7.1 Working of Neural Networks2.7.2 Pros and Cons2.7.3 Applications of Neural Networks2.7.4 How Neural Networks Work?2.7.5 What is an Activation Function?2.7.6 Gradient Descent2.8 Support Vector Machine (SVM)2.8.1 How Does SVM Work?2.8.2 Advantages of SVM2.8.3 Disadvantages of SVM2.8.4 Applications of SVM in Real WorldKey TermsRecapitulation PointsAnswer the QuestionsFill UpState True or FalseMultiple Choice QuestionsCase Study-Based AssignmentEnhancing Audio, Visual and Cognitive SkillsAnswers

3. Artificially Intelligent Machine
3.1 Defining Intelligence3.2 Components of Intelligence3.3 Differences Between Human and Machine Intelligence3.4 Agent and Environment3.4.1 Key Terminology3.4.2 Rationality3.4.3 Structure of Intelligent Agents3.4.4 Types of Agents3.4.5 The Nature of Environments3.4.6 Types of Environments3.5 Search3.5.1 Types of Search Algorithms3.5.2 Properties of Search Algorithms3.6 Uninformed Search Algorithms3.6.1 Depth First Search (DFS)3.6.2 Depth-Limited Search Algorithm (DLS)3.6.3 Breadth First Search (BFS)3.6.4 Uniform Cost Search (UCS)3.6.5 Iterative Deepening Depth-First Search (IDDFS)3.6.6 Bidirectional Search3.7 Informed Search Algorithms3.7.1 Pure Heuristic Search3.7.2 Best-First Search Algorithm (Greedy Search)3.7.3 A* Search Algorithm3.7.4 AO* Algorithm3.8 Hill Climbing Algorithm in Artificial Intelligence3.8.1 Features of Hill Climbing3.8.2 Types of Hill Climbing3.8.3 State Space Diagram for Hill Climbing3.8.4 Simulated Annealing3.8.5 Applications3.8.6 Pros and Cons of Hill Climbing Algorithms3.9 Adversarial Search3.9.1 Game Scenarios3.9.2 Key Terminology3.9.3 Game Tree3.9.4 Uses of Adversarial Search3.9.5 Mini-Max Algorithm3.10 Alpha-Beta Pruning3.10.1 Pseudo-Code for Alpha-Beta Pruning3.10.2 Worst-Case and Best-Case in Alpha-Beta Pruning3.11 Local Search Algorithms3.11.1 Hill-Climbing Search3.11.2 Local Beam Search3.11.3 Simulated Annealing3.11.4 Travelling Salesman Problem3.12 Single Agent Path-Finding Problems3.12.1 Search Terminology3.12.2 Brute-Force Search StrategiesProgrammer’s ZoneKey TermsRecapitulation PointsAnswer the QuestionsFill UpState True or FalseMultiple Choice QuestionsAnswers
4. Knowledge Representation
4.1 Introduction4.2 Knowledge Representation4.2.1 What Knowledge Needs to be Represented?4.2.2 What is Knowledge?4.2.3 What is Logic?4.2.4 Cycle of Knowledge Representation in AI4.2.5 Knowledge Representation Requirements4.3 Knowledge-Based Agent4.3.1 The Architecture of Knowledge-Based Agent4.3.2 Operations Performed By KBA4.3.3 A Generic Knowledge-Based Agent4.3.4 Various Levels of Knowledge-Based Agent4.3.5 Approaches to Designing a Knowledge-Based Agent4.4 Types of Knowledge4.5 Techniques of Knowledge Representation in AI4.5.1 Logical Representation4.5.2 Semantic Network Representation4.5.3 Frame Representation4.5.4 Production Rules4.5.5 Propositional Logic (PL)4.6 Syntax of Propositional Logic4.7 Logical Connectives in Propositional Logic4.7.1 Logical Equivalence4.7.2 Truth Table of Propositional Connectives4.7.3 Precedence of Connectives4.7.4 Properties of Operators4.7.5 Limitations of Propositional Logic4.8 Inference Rules4.8.1 Types of Inference Rules4.8.2 First-Order Logic4.8.3 Generalized Modus Ponens Rule4.8.4 Unification in FOL4.8.5 Unification Algorithm4.8.6 Resolution4.8.7 The Resolution Inference Rule4.8.8 The Resolution Process4.8.9 Explanation of Resolution Graph4.9 Forward Chaining and Backward Chaining in AI4.9.1 Horn Clause and Definite Clause4.9.2 Forward Chaining4.9.3 Forward Chaining Algorithm4.9.4 Why Do We Use Forward Chaining?4.9.5 Backward Chaining4.9.6 Pros and Cons of Backward ChainingProgrammer’s ZoneKey TermsRecapitulation PointsAnswer the QuestionsFill UpState True or FalseMultiple Choice QuestionsAnswers
5. Reasoning and Learning in Artificial Intelligence
5.1 Reasoning5.1.1 Features of a Reasoning System5.1.2 Why Focus on Reasoning System?5.1.3 Methods of Reasoning5.2 Probabilistic Reasoning in Artificial Intelligence5.2.1 Uncertainty5.2.2 Probability5.3 Bayes’ Theorem5.3.1 Bayesian Belief Network in Artificial Intelligence5.3.2 Joint Probability Distribution5.3.3 Understanding the Semantics of Bayesian Network5.4 Learning5.4.1 Components of a Learning System5.4.2 Forms of Learnings5.5 Clustering5.5.1 Clusters5.5.2 Overview of Clustering Techniques5.6 Explanation-Based Learning (EBL)5.7 Reinforcement Learning5.7.1 Components of Reinforcement Learning5.7.2 Example: Reinforcement Learning in Real World5.7.3 Characteristics of Reinforcement Learning5.7.4 Differences Between Reinforcement Learning and Supervised Learning5.7.5 Types of Reinforcement5.7.6 Applications of Reinforcement Learning5.7.7 When to Use Reinforcement Learning in a Large Environment?5.7.8 Benefits of Reinforcement Learning5.7.9 Challenges with Reinforcement Learning5.7.10 Future of Reinforcement Learning5.7.11 When Not to Use Reinforcement Learning?Programmer’s ZoneKey TermsRecapitulation PointsAnswer ThemFill UpState True or FalseMultiple Choice QuestionsAnswers
6. Computer Vision (CV)
6.1 Human Vision vs Computer Vision6.2 How Does Computer Vision Work?6.3 The Evolution of Computer Vision6.4 Tasks in Computer Vision6.5 How Computer Vision Works with Deep Learning?6.6 Applications of Computer Vision6.7 Which Vision Succeeded?6.8 Challenges in Computer Vision6.9 Understanding Image Pixels6.9.1 What is Resolution?6.9.2 DPI and PPI6.10 Convolutional Neural Networks (CNN)6.10.1 Understanding the Working of a Simple CNN6.10.2 THE Pooling Layer6.10.3 Limitations6.11 Working with Images Using OpenCV6.12 Immersive Experience6.12.1 Elements of Immersion6.12.2 Types of Immersive Experiences6.12.3 Applications of Immersive Experiences6.12.4 Virtual Reality Systems6.12.5 Types of Augmented Reality6.12.6 Mixed Reality6.12.7 Challenges of Immersive ExperiencesProgrammer’s ZoneKey TermsRecapitulation PointsReview QuestionsFill UpState True or FalseMultiple Choice QuestionsIdentify the ProcessAnswers
7. Natural Language Processing
7.1 What is Natural Language Processing?7.2 Everyday NLP Examples7.3 Chatbot7.3.1 Open and Closed Chatbots7.3.2 Uses of Chatbots7.3.3 How a Chatbot Works?7.3.4 Types of Chatbots7.4 How Does Natural Language Processing Work?7.5 Components of NLP7.6 Steps in NLPNLP, AI, Machine Learning: What’s the Difference?7.7 Phases of NLPData Pre-ProcessingData Processing7.8 Syntax vs Semantic Analysis7.9 Applications of Natural Language Processing7.10 Pros and Cons of Natural Language ProcessingLimitations of NLP SystemsChallenges7.11 Evolution of Natural Language Processing7.12 Handling Ambiguities7.12.1 Techniques of Ambiguity Resolution7.13 The NLP Model of Perception7.13.1 NLP Communication Model7.13.2 The Five Perceptual Positions7.14 Constituency Grammar7.15 Context-Free Grammar7.15.1 Derivations7.15.2 Using Nominals in CFG7.15.3 Uses of CFG7.15.4 Types of Derivation7.15.5 Parse Tree7.15.6 Ambiguity in CFG7.15.7 Parser7.16 Speech Recognition7.16.1 How Does Speech Recognition Work?7.16.2 Applications of Speech Recognition7.16.3 Algorithms for Speech Recognition7.16.4 Advantages of Speech Recognition7.16.5 Disadvantages of Speech RecognitionProgrammer’s ZoneKey TermsRecapitulation PointsReview QuestionsFill UpState True or FalseMultiple Choice QuestionsAnswers
8. Current Trends in Artificial Intelligence
8.1 AI and Ethical Concerns8.1.1 Ethical Use of Artificial Intelligence8.1.2 Is AI Dangerous? Will Robots Take Over the World?8.1.3 Ethics in AI8.1.4 AI and Bias8.1.5 Towards Ethical and Trustworthy AI8.1.6 Why is Ethical AI Important?8.1.7 Impact of AI on Jobs8.2 AI as a Service (AIaaS)8.2.1 Factors Triggering Growth of AIaaS8.2.2 The Growth of AIaaS8.2.3 Challenges of AIaaS8.2.4 Vendors of AIaaS8.3 Robotics8.3.1 Artificially Intelligent Robot8.3.2 Characteristics of Robots8.3.3 Types of Robots8.3.4 Types of Robots Based on Degree of Human Control8.3.5 Components of a Robot8.3.6 AI Technology Used in Robotics8.3.7 Planning and Navigation8.4 Recent Trends in AI8.4.1 Collaborative Systems8.4.2 Machines Assisting Humans8.4.3 Algorithmic Game Theory and Computational Social Choice8.4.4 Multi-Agents Reinforcement Learning (MARL)8.4.5 Neuromorphic ComputingProgrammer’s ZoneKey TermsRecapitulation PointsReview QuestionsFill UpState True or FalseMultiple Choice QuestionsAnswers
9. Where AI Is Heading Today?
9.1 Expert System9.1.1 Popular Examples of the Expert System9.1.2 Characteristics of an Expert System9.1.3 Components of an Expert System9.1.4 Participants in the Development of Expert System9.1.5 Capabilities of the Expert System9.1.6 Advantages of Expert Systems9.1.7 Limitations of Expert Systems9.1.8 Applications of Expert Systems9.1.9 Expert System Technology9.1.10 Development of Expert Systems9.2 Internet of Things9.2.1 Examples of Applications of IoT9.2.2 IoT Products9.2.3 Challenges9.2.4 Sensors9.3 Artificial Intelligence of Things (AIoT)9.3.1 How Does AIoT Work?9.3.2 Where Does AI Unlock IoT?9.3.3 Applications and Examples of AIoT9.3.4 Benefits and Challenges of AIoT9.3.5 Future of AIoT9.4 Edge Computing9.4.1 Why is Edge Computing Important?9.4.2 Edge Computing Use Cases and Examples9.4.3 Benefits of Edge Computing9.4.4 Challenges of Edge Computing9.4.5 Edge Computing Implementation9.4.6 Edge Computing, IoT and 5G Possibilities9.5 Metaverse9.5.1 Use Cases of Metaverse9.5.2 Where is Metaverse Today?Key TermsRecapitulation PointsReview QuestionsFill UpState True or FalseMultiple Choice QuestionsAnswers
10. AI Evolving with New Age Techniques
10.1 Fuzzy Logic10.1.1 Characteristics of Fuzzy Logic10.1.2 Architecture of a Fuzzy Logic System10.1.3 Membership Function10.1.4 Example of a Fuzzy Logic System10.1.5 Classical and Fuzzy Set Theory10.1.6 Fuzzy Set10.1.7 Applications of Fuzzy Logic10.1.8 Advantages of Fuzzy Logic10.1.9 Disadvantages of Fuzzy Logic10.1.10 Trends10.2 Genetic Algorithms10.2.1 Advantages of Genetic Algorithms10.2.2 Limitations of Genetic Algorithms10.2.3 Basic Terminology10.2.4 Basic Structure10.2.5 Genotype Representation10.2.6 Population10.2.7 Population Initialization10.2.8 Population Models10.2.9 Fitness Function10.2.10 Parent Selection10.2.11 Crossover10.2.12 Mutation10.2.13 Termination Condition10.2.14 Application Areas10.3 Soft Computing10.3.1 Characteristics of Soft Computing10.3.2 Need for Soft Computing10.3.3 Applications of Soft Computing10.3.4 Elements of Soft Computing10.4 Transfer Learning10.4.1 How Transfer Learning Works?10.4.2 When to Use Transfer Learning10.4.3 Approaches to Transfer Learning10.4.4 Traditional Machine Learning vs Transfer Learning10.4.5 Classical Transfer Learning Strategies10.4.6 Transfer Learning for Deep Learning10.4.7 Steps in Transfer Learning10.4.8 Types of Deep Transfer Learning10.4.9 Applications of Transfer Learning10.4.10 When Does Transfer Learning Not Work?Key TermsRecapitulation PointsReview QuestionsFill UpState True or FalseMultiple Choice QuestionsAnswers
Programming Language Prolog
Case Study
Case Study 1: N Queen Problem with Backtracking
Case Study 2: Warnsdorff’s Algorithm For Knight’s Tour Problem
Case Study 3: Rat in a Maze
Case Study 4: Unique Paths in A Grid
Case Study 5: The Wumpus World
Case Study 6: Smart Cities
Index
Copyright

Content preview from Artificial Intelligence: Beyond Classical AI

9 Where AI Is Heading Today?

9.1 Expert System

An expert system is a computer program that solves complex problems in a particular domain, at the level of extra-ordinary human intelligence and expertise. That is, it is designed to provide decisions just like a human expert. Expert systems are the computer applications developed to solve complex problems.

Expert systems are designed for a specific domain, such as medicine, science, etc.

To perform its task, the expert system analyses user queries to extract knowledge from its knowledge base using the reasoning and inference rules.

The first expert system was developed in 1970. This system makes decisions for complex problems using both facts and heuristics like a human expert. The performance ...

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

Deep Learning Illustrated: A Visual, Interactive Guide to Artificial Intelligence

Publisher Resources

ISBN: 9789357053778

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Artificial Intelligence: Beyond Classical AI

by Reema Thareja

9