Atjaunināt sīkdatņu piekrišanu

E-grāmata: Reinforcement Learning for Cyber-Physical Systems: with Cybersecurity Case Studies

, (Pace University, New York City, New York, USA)
  • Formāts: 256 pages
  • Izdošanas datums: 22-Feb-2019
  • Izdevniecība: CRC Press
  • Valoda: eng
  • ISBN-13: 9781351006606
Citas grāmatas par šo tēmu:
  • Formāts - EPUB+DRM
  • Cena: 56,34 €*
  • * ši ir gala cena, t.i., netiek piemērotas nekādas papildus atlaides
  • Ielikt grozā
  • Pievienot vēlmju sarakstam
  • Šī e-grāmata paredzēta tikai personīgai lietošanai. E-grāmatas nav iespējams atgriezt un nauda par iegādātajām e-grāmatām netiek atmaksāta.
Reinforcement Learning for Cyber-Physical Systems: with Cybersecurity Case StudiesPalielināt
  • Formāts: 256 pages
  • Izdošanas datums: 22-Feb-2019
  • Izdevniecība: CRC Press
  • Valoda: eng
  • ISBN-13: 9781351006606
Citas grāmatas par šo tēmu:

DRM restrictions

  • Kopēšana (kopēt/ievietot):

    nav atļauts

  • Drukāšana:

    nav atļauts

  • Lietošana:

    Digitālo tiesību pārvaldība (Digital Rights Management (DRM))
    Izdevējs ir piegādājis šo grāmatu šifrētā veidā, kas nozīmē, ka jums ir jāinstalē bezmaksas programmatūra, lai to atbloķētu un lasītu. Lai lasītu šo e-grāmatu, jums ir jāizveido Adobe ID. Vairāk informācijas šeit. E-grāmatu var lasīt un lejupielādēt līdz 6 ierīcēm (vienam lietotājam ar vienu un to pašu Adobe ID).

    Nepieciešamā programmatūra
    Lai lasītu šo e-grāmatu mobilajā ierīcē (tālrunī vai planšetdatorā), jums būs jāinstalē šī bezmaksas lietotne: PocketBook Reader (iOS / Android)

    Lai lejupielādētu un lasītu šo e-grāmatu datorā vai Mac datorā, jums ir nepieciešamid Adobe Digital Editions (šī ir bezmaksas lietotne, kas īpaši izstrādāta e-grāmatām. Tā nav tas pats, kas Adobe Reader, kas, iespējams, jau ir jūsu datorā.)

    Jūs nevarat lasīt šo e-grāmatu, izmantojot Amazon Kindle.

Reinforcement Learning for Cyber-Physical Systems: with Cybersecurity Case Studies was inspired by recent developments in the fields of reinforcement learning (RL) and cyber-physical systems (CPSs). Rooted in behavioral psychology, RL is one of the primary strands of machine learning. Different from other machine learning algorithms, such as supervised learning and unsupervised learning, the key feature of RL is its unique learning paradigm, i.e., trial-and-error. Combined with the deep neural networks, deep RL become so powerful that many complicated systems can be automatically managed by AI agents at a superhuman level. On the other hand, CPSs are envisioned to revolutionize our society in the near future. Such examples include the emerging smart buildings, intelligent transportation, and electric grids.

However, the conventional hand-programming controller in CPSs could neither handle the increasing complexity of the system, nor automatically adapt itself to new situations that it has never encountered before. The problem of how to apply the existing deep RL algorithms, or develop new RL algorithms to enable the real-time adaptive CPSs, remains open. This book aims to establish a linkage between the two domains by systematically introducing RL foundations and algorithms, each supported by one or a few state-of-the-art CPS examples to help readers understand the intuition and usefulness of RL techniques.

Features











Introduces reinforcement learning, including advanced topics in RL





Applies reinforcement learning to cyber-physical systems and cybersecurity





Contains state-of-the-art examples and exercises in each chapter





Provides two cybersecurity case studies

Reinforcement Learning for Cyber-Physical Systems with Cybersecurity Case Studies is an ideal text for graduate students or junior/senior undergraduates in the fields of science, engineering, computer science, or applied mathematics. It would also prove useful to researchers and engineers interested in cybersecurity, RL, and CPS. The only background knowledge required to appreciate the book is a basic knowledge of calculus and probability theory.
Preface xiii
Author Bios xvii
Section I Introduction
Chapter 1 Overview of Reinforcement Learning
3(18)
1.1 Overview of Reinforcement Learning
4(10)
1.1.1 Introduction
4(2)
1.1.2 Comparison with Other Machine Learning Methods
6(3)
1.1.3 An Example of Reinforcement Learning
9(2)
1.1.4 Applications of Reinforcement Learning
11(3)
1.2 History of Reinforcement Learning
14(4)
1.2.1 Traditional Reinforcement Learning
14(3)
1.2.2 Deep Reinforcement Learning
17(1)
1.3 Simulation Toolkits for Reinforcement Learning
18(2)
1.4 Remarks
20(1)
Chapter 2 Overview of Cyber-Physical Systems and Cyber-security
21(22)
2.1 Introduction
22(2)
2.2 Examples of Cyber-Physical Systems Research
24(5)
2.2.1 Resource Allocation
25(2)
2.2.2 Data Transmission and Management
27(1)
2.2.3 Energy Control
28(1)
2.2.4 Model-Based Software Design
28(1)
2.3 Cybersecurity Threats
29(9)
2.3.1 Adversaries in Cybersecurity
30(1)
2.3.2 Objectives of Cybersecurity
31(1)
2.3.2.1 Confidentiality
32(1)
2.3.2.2 Integrity
33(3)
2.3.2.3 Availability
36(1)
2.3.2.4 Authenticity
36(2)
2.4 Remarks
38(1)
2.5 Exercises
38(5)
Section II Reinforcement Learning for Cyber-Physical Systems
Chapter 3 Reinforcement Learning Problems
43(26)
3.1 Multi-Armed Bandit Problem
43(10)
3.1.1 e-Greedy
48(2)
3.1.2 Softmax Algorithm
50(1)
3.1.3 UCB Algorithm
51(2)
3.2 Contextual Bandit Problem
53(2)
3.2.1 LinUCB Algorithm
54(1)
3.3 Reinforcement Learning Problem
55(8)
3.3.1 Elements of RL
56(2)
3.3.2 Introduction of Markov Decision Process
58(1)
3.3.3 Value Functions
59(4)
3.4 Remarks
63(1)
3.5 Exercises
63(6)
Chapter 4 Model-Based Reinforcement Learning
69(24)
4.1 Introduction
69(4)
4.1.1 Example
70(3)
4.2 Dynamic Programming
73(7)
4.2.1 Policy Iteration
74(2)
4.2.1.1 Example
76(2)
4.2.2 Value Iteration
78(1)
4.2.3 Asynchronous Dynamic Programming
79(1)
4.3 Partially Observable Markov Decision Process
80(5)
4.3.1 Belief MDP
82(3)
4.4 Continuous Markov Decision Process
85(2)
4.4.1 Lazy Approximation
85(2)
4.4.2 Function Approximation
87(1)
4.5 Remarks
87(1)
4.6 Exercises
88(5)
Chapter 5 Model-Free Reinforcement Learning
93(32)
5.1 Introduction to Model-Free RL
93(1)
5.2 RL Prediction
94(6)
5.2.1 Monte Carlo Learning
94(3)
5.2.2 Temporal-Difference (TD) Learning
97(1)
5.2.2.1 TD(0)
98(1)
5.2.2.2 TD(λ)
99(1)
5.3 RL Control
100(16)
5.3.1 Monte Carlo Control
100(1)
5.3.2 TD-Based Control
101(1)
5.3.2.1 Q-Learning
102(1)
5.3.2.2 Example
103(2)
5.3.2.3 Sarsa
105(1)
5.3.2.4 Example
105(3)
5.3.3 Policy Gradient
108(3)
5.3.3.1 Example
111(1)
5.3.4 Actor-Critic
112(2)
5.3.4.1 Example
114(2)
5.4 Advanced Algorithms
116(2)
5.4.1 Expected Sarsa
116(1)
5.4.2 Double Q-Learning
117(1)
5.5 Remarks
118(1)
5.6 Exercises
119(6)
Chapter 6 Deep Reinforcement Learning
125(30)
6.1 Introduction to Deep RL
125(1)
6.2 Deep Neural Networks
126(6)
6.2.1 Convolutional Neural Networks
129(1)
6.2.2 Recurrent Neural Networks
130(2)
6.3 Deep Learning to Value Functions
132(5)
6.3.1 DQN
134(2)
6.3.1.1 Example
136(1)
6.4 Deep Learning to Policy Functions
137(11)
6.4.1 DDPG
140(2)
6.4.2 A3C
142(5)
6.4.2.1 Example
147(1)
6.5 DEEP LEARNING TO RL MODEL
148(1)
6.6 DRL Computation Efficiency
149(1)
6.7 Remarks
150(1)
6.8 Exercises
151(4)
Section III Case Studies
Chapter 7 Reinforcement Learning for Cybersecurity
155(14)
7.1 Traditional Cybersecurity Methods
156(2)
7.1.1 Traditional Cybersecurity Technologies
156(1)
7.1.2 Emerging Cybersecurity Threats
157(1)
7.2 Examples of RL to Cybersecurity Applications
158(7)
7.2.1 Faked Sensing Attacks in Mobile Crowdsensing
159(1)
7.2.2 Security Enhancement in Cognitive Radio Networks
160(2)
7.2.3 Security in Mobile Edge Computing
162(2)
7.2.4 Dynamic Scheduling of Cybersecurity Analysts
164(1)
7.3 Remarks
165(1)
7.4 Exercises
166(3)
Chapter 8 Case Study: Online Cyber-Attack Detection in Smart Grid
169(20)
8.1 Introduction
169(3)
8.2 System Model and State Estimation
172(2)
8.2.1 System Model
172(2)
8.2.2 State Estimation
174(1)
8.3 Problem Formulation
174(5)
8.4 Solution Approach
179(3)
8.5 Simulation Results
182(5)
8.5.1 Simulation Setup and Parameters
182(1)
8.5.2 Performance Evaluation
183(4)
8.6 Remarks
187(2)
Chapter 9 Case Study: Defeat Man-in-the-Middle Attack
189(16)
9.1 Introduction
189(3)
9.2 RL Approach
192(3)
9.2.1 State Space
192(2)
9.2.2 Action Space
194(1)
9.2.3 Reward
195(1)
9.3 Experiments and Results
195(3)
9.3.1 Model Training
196(1)
9.3.2 Online Experiments
197(1)
9.4 Discussions
198(1)
9.4.1 Probe-Based Detection System
198(1)
9.4.2 Make Model Practical with SDN/OpenFlow
199(1)
9.5 Remarks
199(6)
Bibliography 205(22)
Index 227
Chong Li is co-founder of Nakamoto \& Turing Labs Inc. He is Chief Architect and Head of Research at Canonchain Network. He is also an adjunct assistant professor at Columbia University. Dr. Li was a staff research engineer in the department of corporate R&D at Qualcomm Technologies. He received a B.E. in Electronic Engineering and Information Science from Harbin Institute of Technology and a Ph.D in Electrical and Computer Engineering from Iowa State University.

Dr. Lis research interests include information theory, machine learning, blockchain, networked control and communications, coding theory, PHY/MAC design for 5G technology and beyond. Dr. Li has published many technical papers in top-ranked journals, including Proceedings of the IEEE, IEEE Transactions on Information Theory, IEEE Communications Magazine, Automatica, etc. He has served as session chair and technical program committee for a number of international conferences. He has also served as reviewer for many prestigious journals and international conferences, including IEEE Transactions on Information Theory, IEEE Transactions on Wireless Communication, ISIT, CDC, ICC, WCNC, Globecom, etc. He holds 200+ international and U.S. patents (granted and pending) and received several academic awards including the MediaTek Inc. and Wu Ta You Scholar Award, the Rosenfeld International Scholarship and Iowa State Research Excellent Award. At Qualcomm, Dr. Li significantly contributed to the systems design and the standardization of several emerging key technologies, including LTE-D, LTE-controlled WiFi and 5G. At Columbia University, he has been instructing graduate-level courses, such as reinforcement learning, blockchain technology and convex optimization, and actively conducting research in the related field. Recently, Dr. Li has been driving the research and development of blockchain-based geo-distributed shared computing, and managing the patent-related business at Canonchain.

Meikang Qiu received the BE and ME degrees from Shanghai Jiao Tong University and received Ph.D. degree of Computer Science from University of Texas at Dallas. Currently, he is an Adjunct Professor at Columbia University and Associate Professor of Computer Science at Pace University. He is an IEEE Senior member and ACM Senior member. He is the Chair of IEEE Smart Computing Technical Committee. His research interests include cyber security, cloud computing, big data storage, hybrid memory, heterogeneous systems, embedded systems, operating systems, optimization, intelligent systems, sensor networks, etc.
Biežāk uzdotie jautājumi par e-grāmatām Biežāk uzdotie jautājumi par e-grāmatām
Permanent link: https://www.kriso.lv/db/97813510066066e.html
Keywords: