Search

Browse Subject Areas

For Authors

Submit a Proposal

Artificial General Intelligence

Principles and Practices
Edited by T. Saravanan, P. Preethi, Sumaya Sanober, N. Thillaiarasu and S. Balamurugan
Series: Leading-Edge Breakthroughs in Artificial Intelligence
Copyright: 2026   |   Expected Pub Date:2026/05/30
ISBN: 9781394422678  |  Hardcover  |  
472 pages

One Line Description
This comprehensive guide provides an extensive overview of the key theories, methodologies, and applied frameworks that enable AGI systems to exhibit aspects of human intelligence.

Audience
Engineering students, research scholars, IT professionals, network administrators, artificial intelligence and deep learning experts, and government research agencies.

Description
As the role of artificial intelligence grows in our everyday lives, so does the need for AI with greater capabilities. Unlike narrow AI, confined to specific tasks, artificial general intelligence seeks human-like adaptability, reasoning, and learning across domains. Integrating cognitive, mathematical, and computational concepts, it presents multidimensional solutions to create more natural human-AI interactions. This book examines the theoretical foundations, cognitive architectures, and practical methodologies shaping artificial general intelligence. It highlights the significance of human-like emotional intelligence in AI and its potential to create more natural, empathetic, and intuitive human-AI interactions, using techniques such as facial expression analysis, speech emotion recognition, and physiological signal processing. From healthcare to customer service, affective AI is being used to enhance user experiences by tailoring interactions to the emotional states of individuals. The book also discusses the ethical dilemmas posed by affective AI, such as emotional manipulation, bias in emotion detection, and the impact of AI-driven emotional decisions on human behavior. Balancing rigor with practical insight, the volume provides a roadmap for researchers, practitioners, and policymakers to study artificial general intelligence’s evolution and transformative potential.
Readers will find the volume:
• Discusses different applications of affective artificial intelligence across various industries;
• Introduces the fundamental concepts of reinforcement learning for different applications;
• Presents the state-of-the-art of transfer learning analysis through contributions from industry and academia.

Back to Top
Author / Editor Details
T. Saravanan, PhD is an Assistant Professor at the Gandhi Institute of Technology and Management, Bengaluru, India with more than ten years of teaching experience. He has published many research papers, book chapters, and Indian Patents. His research interests include computer networks, fuzzy logic, and wireless sensor networks.

P. Preethi, PhD is an Associate Professor in the Department of Computer Science and Engineering, Kongunadu College of Engineering and Technology, Trichy, Tamil Nadu, India. She has six books and has published 28 articles in international journals and conferences. Her areas of interest include cloud computing, network security, and machine learning.

Sumaya Sanober, PhD works in the Computer Science Department at Old Dominion University, Virginia, United States. She has published many articles in national and international journals and conferences, and serves as a reviewer on multiple boards. Her research interests include machine learning, artificial neural networks, pattern recognition, web services, cloud computing, and testing tools.

N. Thillaiarasu, PhD is an Associate Professor in the School of Computing and Information Technology, REVA University, Bangalore, India, with more than 12 years of teaching experience. He has more than 75 publications to his credit, including articles, books, and book chapters. His areas of interest include cloud computing, security, IoT, and machine learning.

S. Balamurugan, PhD is the Director, Intelligent Research Consultancy Services, Coimbatore, Tamil Nadu, India. He has published 75 books, 300 papers in international journals and conferences, and 300 patents. With 20 years of research on various cutting-edge technologies, he provides expert guidance in technology forecasting and decision-making for leading companies and startups.

Back to Top

Table of Contents
Series Preface
Preface
Part I: Theoretical and Cognitive Foundations of AGI
1. A Unified Framework for Defining Artificial General Intelligence through Cognitive and Theoretical Perspectives
Latha. P., K. Sivakami, K. Selvavinayaki, V. Devi and Karthick R.
1.1 Introduction
1.2 Related Work
1.2.1 The Fragmented Landscape of Existing AGI Definitions
1.2.2 Cognitive Foundations: Insights from Natural Intelligence
1.2.3 Theoretical Frameworks: Formalizing Intelligence
1.2.4 Bridging Attempts and the Unification Imperative
1.3 Proposed Methodology
1.3.1 Cognitive Architecture Modeling for AGI Foundations
1.3.2 Learning and Adaptation through Meta-Cognitive Feedback
1.3.3 Theoretical Integration Using Algorithmic Information and Goal Modeling
1.4 Evaluation of the Unified AGI Framework
1.5 Conclusion
Bibliography
2. The Role of Theoretical Intelligence in Guiding the Development of Robust Artificial General Intelligence Systems
R. Mekala, Abiramasundari S., A.S. Narmadha, K. N. Jayapriya, M. Maheswaran and Karthikha Sree J.B.
2.1 Introduction
2.1.1 Formal Frameworks for Intelligence: Beyond Heuristic Approaches
2.1.2 Unification Theories of Cognition: Bridging Symbolic, Neural, and Embodied Intelligence
2.2 Related Work
2.2.1 Solomonoff Induction and Algorithmic Learning Theory in AGI
2.2.2 Bayesian Inference and Probabilistic Cognitive Architectures
2.2.3 Computational Rationality and Decision-Theoretic AGI Models
2.2.4 Formal Epistemology, Logic, and Safety in Theoretical AGI
2.3 Proposed Methodology for Developing Theoretically Grounded AGI Systems
2.3.1 Formal Architecture Design: Building AGI on Mathematical Foundations
2.3.2 Theory-Guided Learning Frameworks: From Data Efficiency to Generalization
2.3.3 Verification and Alignment Protocols: Ensuring Safety and Interpretability
2.4 Results
2.4.1 Evaluating Data Efficiency via Solomonoff-Inspired Compression Learning
2.4.2 Performance of Bayesian Meta-Learning in Uncertain Environments
2.4.3 RMR Enhances Planning and Efficiency
2.4.4 Safety and Interpretability Gains from Formal Logic‑Based Control
2.5 Conclusion
References
3. A Comparative Analysis of Cognitive Models Used in Symbolic and Neural Architectures for AGI
Beaulah David, Vanitha. G., K. Kalpana, P. Gokila, N. Logeshwari and Varnikha Sree J.B.
3.1 Introduction
3.1.1 Cognitive Processing: Logic-Driven Inference versus Pattern-Driven Activation
3.1.2 Knowledge Representation: Explicit Symbols versus Distributed Embeddings
3.2 Related Work
3.2.1 Symbolic Cognitive Architectures in AGI
3.2.2 Neural Architectures as Cognitive Models
3.2.3 Hybrid and Neurosymbolic Approaches
3.2.4 Evaluation Metrics and Benchmarks for AGI Cognition
3.3 Proposed Methodology for Developing Explainable AGI through Hybrid Cognitive Architectures
3.3.1 Neurosymbolic Integration for Transparent Reasoning
3.3.2 Meta-Learning for Adaptive Generalization
3.3.3 Interactive Learning for Continuous Knowledge Refinement
3.4 Results
3.4.1 Performance on Symbolic Reasoning Tasks
3.4.2 Generalization across Compositional Tasks
3.4.3 Interpretability and Explanation Quality
3.4.4 Lifelong and Transfer Learning Performance
3.5 Conclusion
References
Part II: Cognitive Architectures and Reasoning Mechanisms
4. Exploring the Role of Cognitive Architectures in Building Human-Like Artificial General Intelligence Systems
Gokilavani A., Abhirami J. S., V. Devi, Gokila Deepa G. and Janani S.
4.1 Introduction
4.1.1 Why CAs? Filling the Holes Left by Narrow and Hybrid AI
4.1.2 Core Challenges in Engineering Human-Like Cognition: Scalability, Emergence, and Embodiment
4.2 Related Work: Evolution and Divergence in CAs for AGI
4.2.1 Symbolic versus Connectionist Paradigms: The Foundational Schism
4.2.2 Hybrid Architectures: Bridging the Cognitive Gap
4.2.3 Evaluation Frameworks: The Metrics Crisis
4.2.4 Emerging Frontiers: Embodiment and Predictive Processing
4.3 Proposed Methodology
4.3.1 Modular Cognitive Design
4.3.2 Memory and Learning Mechanisms
4.3.3 Decision-Making and Goal Optimization
4.4 Results
4.4.1 Modular Cognitive Efficiency
4.4.2 Memory Learning Dynamics
4.4.3 Decision-Making Accuracy Under Constraints
4.5 Conclusion
Bibliography
5. Symbolic and Subsymbolic Reasoning Integration for Flexible and Context-Aware AGI Cognitive Processes
Saisuman Singamsetty
5.1 Introduction
5.1.1 Hybrid Neural-Symbolic Architectures and Representational Bridges
5.1.2 Dynamic Grounding and Contextualized Reasoning Mechanisms
5.2 Related Work
5.2.1 Symbolic Reasoning in Classic AI Systems
5.2.2 Subsymbolic Learning and Neural Representations
5.2.3 Neurosymbolic Integration Models
5.2.4 Cognitive Architectures That Bridge Symbolic and Subsymbolic Layers
5.3 Proposed Methodology
5.3.1 Dual-Process Cognitive Architecture for Integrated Reasoning
5.3.2 Differentiable Neurosymbolic Inference Mechanism
5.3.3 Meta-Cognitive Controller for Reasoning Arbitration and Adaptation
5.4 Results
5.4.1 VQA with Hybrid Reasoning
5.4.2 Common-Sense Inference and Causal Reasoning
5.4.3 Cross-Domain Task Adaptation with Meta-Cognitive Control
5.4.4 Lifelong Learning and Knowledge Retention
5.5 Conclusion
References
6. Developing Common-Sense Reasoning Capabilities in AGI Using Hybrid Neural-Symbolic Learning Approaches
Arunkumar Medisetty and R. Asokan
6.1 Introduction
6.1.1 Neural Acquisition, Grounding, and Emergence of Symbolic Common-Sense Primitives
6.1.2 Compositional Reasoning and Inference with Probabilistic Symbolic Structures
6.2 Related Work
6.2.1 Symbolic Approaches to Common-Sense Reasoning
6.2.2 Neural Network–Based Approaches for Implicit Reasoning
6.2.3 Hybrid Neural-Symbolic Systems in AGI
6.2.4 Meta-Learning and Rule Induction for Common-Sense Acquisition
6.3 Proposed Methodology
6.3.1 Neurosymbolic Knowledge Encoding Framework
6.3.2 Dynamic Rule Learning and Belief Update Mechanism
6.3.3 Common-Sense Reasoning via Contextual Graph Inference
6.3.4 SSL for Common-Sense Embedding Generation
6.4 Results
6.4.1 Performance of Neurosymbolic Knowledge Encoding in Common Sense
6.4.2 Dynamic Rule Learning and Belief Revision in Incremental Tasks
6.4.3 Contextual Graph Inference and Reasoning Accuracy in Multihop QA
6.5 Conclusion
References
7. Designing Explainable Artificial General Intelligence through Transparent and Interpretable Reasoning Mechanisms
Sudheer Singamsetty
7.1 Introduction
7.1.1 Architectural Transparency: Designing for Inherent Inspectability
7.1.2 Interpretable Reasoning Processes: Making the “Thought” Steps Understandable
7.2 Related Work
7.2.1 Explainability in Machine Learning Models
7.2.2 Neurosymbolic Integration for Interpretable Reasoning
7.2.3 Cognitive Architectures for XAGI
7.2.4 Human-Centered Explainable AI and Interaction Models
7.3 Proposed Methodology
7.3.1 Cognitive Reasoning Engine: Symbolic and Probabilistic Inference Core
7.3.2 Interpretable Neural Module: Deep Representation with Embedded Explainability
7.3.3 Meta-Explanation Layer: Bridging Symbolic and Subsymbolic Decisions
7.4 Results
7.4.1 Evaluation of CRE: Logical Accuracy and Inference Traceability
7.4.2 INM: Concept Bottlenecks and Prototype Effectiveness
7.4.3 Meta-Explanation Layer: Human Evaluation of Explanation Quality
7.4.4 Comparative Analysis: Explainability versus Performance Trade-Offs
7.5 Conclusion
References
Part III: Learning Paradigms for Generalization and Adaptability
8. Self-Supervised Learning Approaches for Enhancing the Adaptability of Artificial General Intelligence Models
R. Pushpalakshmi, G. Kalaiarasi, C. P. Thamil Selvi, Nithya C. and D. Satheesh Kumar
8.1 Introduction
8.1.1 Foundation Learning through Generative and Contrastive Pretext Tasks
8.1.2 Enabling Transfer and Meta-Learning through Universal Representations
8.2 Related Work
8.2.1 Basis of SSL in Deep Neural Networks
8.2.2 SSL in Embodied and Interactive Environments
8.2.3 SSL-Based Meta-Learning and Continual Adaptation in AGI
8.2.4 Theoretical Perspectives on Self-Supervised Objectives for General Intelligence
8.3 Proposed Methodology: SSL-Based Framework for AGI Adaptability
8.3.1 Contrastive Representation Learning
8.3.2 Predictive Modeling with Temporal Abstraction
8.3.3 Meta-Cognitive Adaptation through Internal Feedback
8.4 Results
8.4.1 Generalization Performance via Contrastive Pretraining
8.4.2 Temporal Prediction and Long-Term Forecasting
8.4.3 Meta-Cognitive Feedback for Adaptive Control
8.5 Conclusion
References
9. Meta-Learning and Transfer Learning Techniques for Enabling Generalization in AGI Across Multiple Domains
B. Nagarajan, A. Jayanthi, Wasim Raja A., E. Angel Anna Prathiba, Sika K. and Kiran Kumar Thoti
9.1 Introduction
9.1.1 Transfer Learning: Leveraging Foundational Knowledge and Representation Reuse
9.1.2 Meta-Learning: Optimizing the Adaptation Algorithm for Rapid Generalization
9.2 Related Work
9.2.1 Meta-Learning for Few-Shot and Fast Adaptation
9.2.2 Transfer Learning in Multidomain Environments
9.2.3 Meta-Transfer Learning: Bridging Strategies
9.2.4 Preclusion of Catastrophic Forgetting and Continual Learning
9.3 Proposed Methodology
9.3.1 Hierarchical Meta-Learning for Cross-Task Adaptation
9.3.2 Modular Transfer Learning with Context-Aware Reusability
9.3.3 Lifelong Learning via Meta-Regularized Memory Consolidation
9.4 Results
9.4.1 Meta-Learning Performance
9.4.2 Transfer Learning Efficiency
9.4.3 Continual Learning Stability
9.5 Conclusion
References
10. Human-Level Generalization in AGI through Interactive Meta-Learning and Environmental Adaptation
Shylaja Chityala
10.1 Introduction
10.1.1 Interactive Meta-Learning: Learning How to Learn in the Wild
10.1.2 Multimodal Environmental Adaptation: Building Situated, Contextual Understanding
10.2 Related Work
10.2.1 Meta-Learning for Rapid Adaptation
10.2.2 Environmental Adaptation in Cognitive and Artificial Systems
10.2.3 Interactive Learning and Human-in-the-Loop AI
10.2.4 Generalization Benchmarks and Evaluating AGI Flexibility
10.3 Proposed Methodology
10.3.1 IML Loop for Learning-to-Learn Dynamics
10.3.2 Environmental Adaptation via Context-Aware Cognitive Modulation
10.3.3 Human-Guided Refinement and Explanation-Driven Learning
10.4 Results
10.4.1 Few-Shot and Zero-Shot Generalization Performance
10.4.2 Interactive Learning Efficiency and Feedback Utilization
10.5 Contextual Adaptation and Robustness under Distributional Shifts
10.6 Explanation Utility and User Satisfaction in Learning Tasks
10.7 Conclusion
Bibliography
Part IV: Decision-Making, Uncertainty, and Reinforcement Learning
11. Reinforcement Learning for AGI Model–Based versus Model-Free Approaches
Shivamma D., Shaila S.G., Ramesh Chundi and Monish L.
11.1 Introduction
11.2 Fundamentals of AGI
11.3 Model-Free Approaches in AGI
11.3.1 Key Characteristics
11.3.2 Challenges of Model-Free Approaches
11.3.3 Applications of Model-Free Approaches in AGI
11.4 Model-Based Approaches in AGI
11.4.1 Key Characteristics of Model-Based Approaches in AGI
11.4.2 Key Components of Model-Based Approaches in AGI
11.4.3 Challenges of Model-Based Approaches in AGI
11.4.4 Algorithm
11.5 Model-Free versus Model-Based Approaches in AGI
11.6 Conclusion
References
12. InvisiDroid: Practical Evasion of ML-Based Black-Box Web Spyware Classifiers
M. Martinaa, S. Aravindh, S. Gokulraj and M. Tamil Thendral
12.1 Introduction
12.1.1 Contributions of Research Work
12.2 Related Work
12.3 Background
12.3.1 ML-Based Web Spyware Detection
12.3.2 Combative Transformations
12.4 Proposed Methodology
12.4.1 Threat Model
12.4.2 Proposed Framework
12.4.2.1 Preparation Phase
12.4.2.2 Donor Selection and Gadget Extraction Phase
12.4.2.3 Manipulation Phase
12.5 Simulation Results
12.5.1 Target Detection
12.5.2 Dataset
12.5.3 Performance Metrics
12.6 Conclusions
References
Part V: Multimodal Perception and Future Directions
13. Multimodal Perception Systems for AGI: Integrating Visual, Auditory, and Linguistic Information Sources
Tayar Yerramsetty
13.1 Introduction
13.1.1 Unified Multimodal Representation Learning and Cross-Modal Alignment
13.1.2 Neurosymbolic Grounding and Situational Awareness Generation
13.2 Related Work
13.2.1 Visual–Linguistic Integration in Multimodal Learning
13.2.2 Language Grounding and Auditory Perception
13.2.3 Unified Multimodal Embedding and Cross-Attention Mechanisms
13.2.4 Multimodal Reasoning in AGI Systems
13.3 Proposed Methodology
13.3.1 Multistream Encoder Architecture for Modality-Specific Feature Extraction
13.3.2 Cross-Modal Attention Fusion with Dynamic Gating
13.3.3 Hierarchical Episodic Memory for Multimodal Context Retention
13.3.4 Multimodal Commonsense Inference Module
13.3.5 Multimodal Commonsense Inference Engine
13.4 Summary of Results in Multimodal Perception for AGI
13.4.1 Evaluation of Modality-Specific Encoders
13.4.2 Cross-Modal Fusion Performance in Complex Tasks
13.4.3 Episodic Memory and Continual Learning Results
13.4.4 Multimodal Commonsense Reasoning Results
13.5 Conclusion
References
14. Multimodal Learning and Perceptron—Integrating Vision, Language, and Auditory Data
Sindhu A., Suresh Arumugam, Shaila S.G., Monish L. and Ramesh Chundi
14.1 Introduction
14.2 Fundamentals of Perceptron and Neural Networks
14.3 Representing Different Modalities
14.4 Building Intelligent Systems through Multimodal Representation
14.5 Multimodal Fusion Techniques
14.6 Architectures and Models for Multimodal Learning
14.7 Applications of Multimodal AI
14.8 Challenges in Multimodal Integration
14.9 Future Directions in Multimodal Learning
14.10 Conclusion
References
15. TransGAN for Visual Anomaly Detection on Imbalanced Industrial Datasets
Srinivasa Perumal R., Venkatasubramanian A., Premalatha M. and Braveen M.
15.1 Introduction
15.2 Related Works
15.3 Methodology
15.3.1 System Overview
15.3.2 TransGAN Model
15.3.3 Walking through Latent Space for Anomaly Detection
15.3.4 Anomaly Detection in Imbalanced Dataset
15.4 Experimentation and Results
15.4.1 Datasets
15.4.2 Training Details
15.4.2.1 MVTec-AD Dataset
15.4.2.2 For CIFAR-10 Dataset
15.5 Conclusion and Future Work
Bibliography
16. Recent Development of Machine Learning Models for Grape Plant Disease Detection: A Review
M. Anuradha, G. Revathy and M. A. Mohamed Aslam
16.1 Introduction
16.2 Role of AI in Modern Farming
16.3 An Overview of ML and DL Industry in Agricultural Sector
16.4 Detection of Grape Leaf Disease with Transfer Learning–Based Technologies
16.5 Results and Discussion
16.6 Conclusion
References
17. Precision Plant Pathology: Real‑Time Disease Detection Using Deep Learning
M. Martinaa, Pokkuluri Kiran Sree, S. Senthilvadivu and M. Shyamalagowri
17.1 Introduction
17.1.1 Problem Statement
17.1.2 Research Progression: Our Contribution
17.2 Related Works
17.3 Proposed Methodology
17.3.1 Dataset Collection and Annotation
17.3.2 Data Cleaning
17.3.3 Data Preprocessing
17.3.4 Data Augmentation
17.3.5 Dataset Splitting and DV
17.3.6 Model Building
17.3.6.1 DL Models
17.3.7 TensorFlow Serving Model Conversion
17.3.8 Development Phase
17.4 Experimental Results
17.4.1 Performance Assessment for Disease Detection in Individual Plants
17.4.1.1 Performance Assessment of the Apple Plants
17.4.1.2 Performance Assessment of the Tomato Plants
17.4.1.3 Performance Assessment of the Potato Plants
17.4.1.4 Performance Assessment of the Pepper Bell Plants
17.5 Conclusion
References
18. Combining AI and Sensor Fusion Technology for Improving Mobility Solutions Designed for Visually Impaired Users
M.A. Mohamed Aslam, G. Revathy, A. Gayathri, M. Krithika and B. M. Shruthi
18.1 Introduction
18.2 Various Datasets for Training DL Models
18.3 Approaches in the Area of Item Detection and Distance Estimation
18.4 Aids for Visual Object Recognition and Distance Measuring
18.5 Evaluation Criteria and Comparative Study
18.6 Object Identification at Varying Distances
18.7 Conclusion
References
19. Future of Artificial General Intelligence: Quantum Computing, Brain–Computer Interfaces, and AGI Evolution
Youddha Beer Singh, Aditya Dev Mishra and T. Saravanan
19.1 Introduction
19.2 AGI and Quantum Computing
19.2.1 AI Quantum Speedup
19.2.2 ML at the Quantum Level
19.2.3 Prospects for the Future and Challenges in AGI and Quantum Computing
19.3 AGI and BCIs
19.3.1 AGI Neural Interfaces
19.3.2 Augmenting Cognition
19.3.3 Security and Ethical Issues
19.4 The Development of General AI
19.4.1 Evolution of Decision Systems Driven by AGI
19.4.2 AGI from Narrow AI
19.4.3 Self-Education and Independence
19.4.4 Super Intelligence and the Future of Post-AGI
19.5 Future Research Directions
19.6 Conclusion
Abbreviations
References
Index

Back to Top



Description
Author/Editor Details
Table of Contents
Bookmark this page