Artificial intelligence and quantum computing for advanced wireless networks / Savo G. Glisic, Beatriz Lorenzo.

Includes bibliographical references and index.

Table of Contents

Preface, xiii

Part I Artificial Intelligence, 1

1 Introduction, 3

1.1 Motivation, 3

1.2 Book Structure, 5

2 Machine Learning Algorithms, 17

2.1 Fundamentals, 17

2.2 ML Algorithm Analysis, 37

3 Artificial Neural Networks, 55

3.1 Multi-layer Feedforward Neural Networks, 55

3.2 FIR Architecture, 60

3.3 Time Series Prediction, 68

3.4 Recurrent Neural Networks, 69

3.5 Cellular Neural Networks (CeNN), 81

3.6 Convolutional Neural Network (CoNN), 84

4 Explainable Neural Networks, 97

4.1 Explainability Methods, 99

4.2 Relevance Propagation in ANN, 103

4.3 Rule Extraction from LSTM Networks, 110

4.4 Accuracy and Interpretability, 112

5 Graph Neural Networks, 135

5.1 Concept of Graph Neural Network (GNN), 135

5.2 Categorization and Modeling of GNN, 144

5.3 Complexity of NN, 156

6 Learning Equilibria and Games, 179

6.1 Learning in Games, 179

6.2 Online Learning of Nash Equilibria in Congestion Games, 196

6.3 Minority Games, 202

6.4 Nash Q-Learning, 204

6.5 Routing Games, 211

6.6 Routing with Edge Priorities, 220

7 AI Algorithms in Networks, 227

7.1 Review of AI-Based Algorithms in Networks, 227

7.2 ML for Caching in Small Cell Networks, 237

7.3 Q-Learning-Based Joint Channel and Power Level Selection in Heterogeneous Cellular Networks, 243

7.4 ML for Self-Organizing Cellular Networks, 252

7.5 RL-Based Caching, 267

7.6 Big Data Analytics in Wireless Networks, 274

7.7 Graph Neural Networks, 279

7.8 DRL for Multioperator Network Slicing, 291

7.9 Deep Q-Learning for Latency-Limited Network Virtualization, 302

7.10 Multi-Armed Bandit Estimator (MBE), 317

7.11 Network Representation Learning, 327

Part II Quantum Computing, 361

8 Fundamentals of Quantum Communications, 363

8.1 Introduction, 363

8.2 Quantum Gates and Quantum Computing, 372

8.3 Quantum Fourier Transform (QFT), 386

9 Quantum Channel Information Theory, 397

9.1 Communication Over a Channel, 398

9.2 Quantum Information Theory, 401

9.3 Channel Description, 407

9.4 Channel Classical Capacities, 414

9.5 Channel Quantum Capacity, 431

9.6 Quantum Channel Examples, 437

10 Quantum Error Correction, 451

10.1 Stabilizer Codes, 458

10.2 Surface Code, 465

10.3 Fault-Tolerant Gates, 471

10.4 Theoretical Framework, 474

11 Quantum Search Algorithms, 499

11.1 Quantum Search Algorithms, 499

11.2 Physics of Quantum Algorithms, 510

12 Quantum Machine Learning, 543

12.1 QML Algorithms, 543

12.2 QNN Preliminaries, 547

12.3 Quantum Classifiers with ML: Near-Term Solutions, 550

12.4 Gradients of Parameterized Quantum Gates, 560

12.5 Classification with QNNs, 568

12.6 Quantum Decision Tree Classifier, 575

13 QC Optimization, 593

13.1 Hybrid Quantum-Classical Optimization Algorithms, 593

13.2 Convex Optimization in Quantum Information Theory, 601

13.3 Quantum Algorithms for Combinatorial Optimization Problems, 609

13.4 QC for Linear Systems of Equations, 614

13.5 Quantum Circuit, 625

13.6 Quantum Algorithm for Systems of Nonlinear Differential Equations, 628

14 Quantum Decision Theory, 637

14.1 Potential Enablers for Qc, 637

14.2 Quantum Game Theory (QGT), 641

14.3 Quantum Decision Theory (QDT), 665

14.4 Predictions in QDT, 676

15 Quantum Computing in Wireless Networks, 693

15.1 Quantum Satellite Networks, 693

15.2 QC Routing for Social Overlay Networks, 706

15.3 QKD Networks, 713

16 Quantum Network on Graph, 733

16.1 Optimal Routing in Quantum Networks, 733

16.2 Quantum Network on Symmetric Graph, 744

16.3 QWs, 747

16.4 Multidimensional QWs, 753

17 Quantum Internet, 773

17.1 System Model, 775

17.2 Quantum Network Protocol Stack, 789

References, 814

Index, 821

"By increasing the density and number of different functionalities in wireless networks there is more and more need for the use of artificial intelligence for planning network deployment, running their optimization and dynamically controlling their operation. For example, machine learning algorithms are used for the prediction of traffic and network state in order to timely reserve resources for smooth communication with high reliability and low latency; Big data mining is used to predict customer behaviour and pre-distribute the information content across the network so that it can be efficiently delivered as soon as requested; Intelligent agents can search the internet on behalf of the customer in order to find the best options when it comes to buying any product online. This timely book presents a review of AI-based learning algorithms with a number of case studies supported by Python and R programs, providing a discussion of the learning algorithms used in decision making based on game theory and a number of specific applications in wireless networks, such as channel, network state and traffic prediction. It is expected that once quantum computing becomes a commercial reality, it will be used in wireless communications systems in order to speed up specific processes due to its inherent parallelization capabilities. This is a practical book packed with case studies and follows a basic through to advanced level path and is an ideal course accompaniment for graduate/masters students, and online professional study."-- Provided by publisher.

About the Author

Savo G. Glisic is Research Professor at Worcester Polytechnic Institute, Massachusetts, USA. His research interests include network optimization theory, network topology control and graph theory, cognitive networks, game theory, artificial intelligence, and quantum computing technology.

Beatriz Lorenzo is Assistant Professor in the Department of Electrical and Computer Engineering at the University of Massachusetts Amherst, USA. Her research interests include the areas of communication networks, wireless networks, and mobile computing.