Cover -- Preface -- Contents -- Chapter 1. Introduction -- 1.1 Fuzzy Logic (FL) -- 1.2 Neural Networks (NN) -- 1.3 Similarities and Dissimilarities Between FL and NN -- 1.4 Applications -- Question Bank -- References -- Chapter 2. Fuzzy Sets and Fuzzy Logic -- 2.1 Introduction -- 2.2 What is Fuzzy Logic? -- 2.3 Historical Background -- 2.4 Characteristics of Fuzzy Logic -- 2.5 Characteristics of Fuzzy Systems -- 2.6 Fuzzy Sets -- 2.6.1 Fuzzy Set -- 2.6.2 Support -- 2.6.3 Normal Fuzzy Set -- 2.6.4 a-Cut -- 2.6.5 Convex Fuzzy Set -- 2.6.6 Fuzzy Number -- 2.6.7 Quasi Fuzzy Number -- 2.6.8 Triangular Fuzzy Number -- 2.6.9 Trapezoidal Fuzzy Number -- 2.6.10 Subsethood -- 2.6.11 Equality of Fuzzy Sets -- 2.6.12 Empty Fuzzy Set -- 2.6.13 Universal Fuzzy Set -- 2.6.14 Fuzzy Point -- 2.7 Operations on Fuzzy Sets -- 2.7.1 Intersection -- 2.7.2 Union -- 2.7.3 Complement -- Question Bank -- References -- Chapter 3.Fuzzy Relations -- 3.1 Introduction -- 3.2 Fuzzy Relations -- 3.2.1 Classical N-Array Relation -- 3.2.2 Reflexivity -- 3.2.3 Anti-Reflexivity -- 3.2.4 Symmetricity -- 3.2.5 Anti-Symmetricity -- 3.2.6 Transitivity -- 3.2.7 Equivalence -- 3.2.8 Partial Order -- 3.2.9 Total Order -- 3.2.10 Binary Fuzzy Relation -- 3.3 Operations on Fuzzy Relations -- 3.3.1 Intersection -- 3.3.2 Union -- 3.3.3 Projection -- 3.3.4 Cartesian Product of two Fuzzy Sets -- 3.3.5 Shadow of Fuzzy Relation -- 3.3.6 Sup-Min Composition of Fuzzy Relations -- Question Bank -- References -- Chapter 4. Fuzzy Implications -- 4.1 Introduction -- 4.2 Fuzzy Implications -- 4.3 Modifiers -- 4.3.1 Linguistic Variables -- 4.3.2 the Linguistic Variable Truth -- Question Bank -- References -- Chapter 5. The Theory of Approximate Reasoning -- 5.1 Introduction -- 5.2 Translation Rules -- 5.2.1 Entailment Rule -- 5.2.2 Conjunction Rule -- 5.2.3 Disjunction Rule -- 5.2.4 Projection Rule.

5.2.5 Negation Rule -- 5.2.6 Compositional Rule of Inference -- 5.3 Rational Properties -- 5.3.1 Basic Property -- 5.3.2 Total Indeterminance -- 5.3.3 Subset -- 5.3.4 Superset -- Question Bank -- References -- Chapter 6. Fuzzy Rule-Based Systems -- 6.1 Introduction -- 6.2 Triangular Norm -- 6.3 Triangular Conorm -- 6.4 t-Norm-Based Intersection -- 6.5 t-Conorm-Based Union -- 6.6 Averaging Operators -- 6.6.1 An Averaging Operator is a Function -- 6.6.2 Ordered Weighted Averaging -- 6.7 Measure of Dispersion or Entropy of an Owa Vector -- 6.8 Mamdani System -- 6.9 Larsen System -- 6.10 Defuzzification -- Question Bank -- References -- Chapter 7. Fuzzy Reasoning Schemes -- 7.1 Introduction -- 7.2 Fuzzy Rule-Base System -- 7.3 Inference Mechanisms in Fuzzy Rule-Base Systems -- 7.3.1 Mamdani Inference Mechanism -- 7.3.2 Tsukamoto Inference Mechanism -- 7.3.3 Sugeno Inference Mechanism -- 7.3.4 Larsen Inference Mechanism -- 7.3.5 Simplified Fuzzy Reasoning -- Question Bank -- References -- Chapter 8. Fuzyy Logic Controllers -- 8.1 Introduction -- 8.2 Basic Feedback Control System -- 8.3 Fuzzy Logic Controller -- 8.3.1 Two-Input-Single-Output (TISO) Fuzzy Systems -- 8.3.2 Mamdani Type of Fuzzy Logic Control -- 8.3.3 Fuzzy Logic Control Systems -- 8.4 Defuzzification Methods -- 8.4.1 Center-of-Area/Gravity -- 8.4.2 First-of-Maxima -- 8.4.3 Middle-of-Maxima -- 8.4.4 Max-Criterion -- 8.4.5 Height Defuzzification -- 8.5 Effective of Fuzzy Logic Control Systems -- Question Bank -- References -- Chapter 9. Fuzzy Logic Applications -- 9.1 Why Use Fuzzy Logic? -- 9.2 Applications of Fuzzy Logic -- 9.3 When Not to use Fuzzy Logic? -- 9.4 Fuzzy Logic Model for Prevention of Road Accidents -- 9.4.1 Traffic Accidents and Traffic Safety -- 9.4.2 Fuzzy Logic Approach -- 9.4.3 Application -- 9.4.4 Membership Functions -- 9.4.5 Rule Base -- 9.4.6 Output.

9.4.7 Conclusions -- 9.5 Fuzzy Logic Model to Control Room Temperature -- 9.5.1 The Mechanics of Fuzzy Logic -- 9.5.2 Fuzzification -- 9.5.3 Rule Application -- 9.5.4 Defuzzification -- 9.5.5 Conclusions -- 9.6 Fuzzy Logic Model for Grading of Apples -- 9.6.1 Apple Defects Used in the Study -- 9.6.2 Materials and Methods -- 9.6.3 Application of Fuzzy Logic -- 9.6.4 Fuzzy Rules -- 9.6.5 Determination of Membership Functions -- 9.6.6 Defuzzification -- 9.6.7 Results and Discussion -- 9.6.8 Conclusion -- 9.7 An Introductory Example: Fuzzy V/S Non-Fuzzy -- 9.7.1 The Non-Fuzzy Approach -- 9.7.2 The Fuzzy Approach -- 9.7.3 Some Observations -- Question Bank -- References -- Chapter 10. Neural Networks Fundamentals -- 10.1 Introduction -- 10.2 Biological Neural Network -- 10.3 A Framework for Distributed Representation -- 10.3.1 Processing Units -- 10.3.2 Connections Between Units -- 10.3.3 Activation and Output Rules -- 10.4 Network Topologies -- 10.5 Training of Artificial Neural Networks -- 10.5.1 Paradigms of Learning -- 10.5.2 Modifying Patterns of Connectivity -- 10.6 Notation and Terminology -- 10.6.1 Notation -- 10.6.2 Terminology -- Question Bank -- References -- Chapter 11. Perceptron and Adaline -- 11.1 Introduction -- 11.2 Networks with Threshold Activation Functions -- 11.3 Perceptron Learning Rule and Convergence Theorem -- 11.3.1 Perceptron Learning Rule -- 11.3.2 Convergence Theorem -- 11.4 Adaptive Linear element (Adaline) -- 11.5 The Delta Rule -- 11.6 Exclusive-or Problem -- 11.7 Multi-Layer Perceptrons can do Everything -- Question Bank -- References -- Chapter 12. Back-Propagation -- 12.1 Introduction -- 12.2 Multi-Layer Feed-Forward Networks -- 12.3 The Generalised Delta Rule -- 12.3.1 Understanding Back-Propagation -- 12.4 Working with Back-Propagation -- 12.4.1 Weight Adjustment with Sigmoid Activation Function.

12.4.2 Learning Rate and Momentum -- 12.4.3 Learning Per Pattern -- 12.5 Other Activation Functions -- 12.6 Deficiencies of Back- Propagation -- 12.6.1 Network Paralysis -- 12.6.2 Local Minima -- 12.7 Advanced Algorithms -- 12.8 How Good are Multi-Layer Feed-Forward Networks? -- 12.8.1 The Effect of the Number of Learning Samples -- 12.8.2 The Effect of the Number of Hidden Units -- 12.9 Applications -- Question Bank -- References -- Chapter 13. Recurrent Networks -- 13.1 Introduction -- 13.2 The Generalized Delta-Rule in Recurrent Networks -- 13.2.1 The Jordan Network -- 13.2.2 The Elman Network -- 13.2.3 Back-Propagation in Fully Recurrent Networks -- 13.3 The Hopfield Network -- 13.3.1 Description -- 13.3.2 Hopfield Network as Associative Memory -- 13.3.3 Neurons with Graded Response -- 13.3.4 Hopfield Networks for Optimization Problems -- 13.4 Boltzmann Machines -- Question Bank -- References -- Chapter 14. Self-Organizing Networks -- 14.1 Introduction -- 14.2 Competitive Learning -- 14.2.1 Clustering -- 14.2.2 Vector Quantisation -- 14.2.3 Counter Propagation -- 14.2.4 Learning Vector Quantisation -- 14.3 Kohonen Network -- 14.4 Principal Component Networks -- 14.4.1 Normalized Hebbian Rule -- 14.4.2 Principal Component Extractor -- 14.4.3 More Eigenvectors -- 14.5 Adaptive Resonance Theory -- 14.5.1 Background: Adaptive Resonance Theory -- 14.5.2 ART 1: The Simplified Neural Network Model -- 14.5.3 Operation -- 14.5.4 ART 1: The Original Model -- 14.5.5 Normalization of the Original Model -- 14.5.6 Contrast Enhancement -- Question Bank -- References -- Chapter 15. Reinforcement Learning -- 15.1 Introduction -- 15.2 The Critic -- 15.3 The Controller Network -- 15.4 Barto's Approach: The ASE-ACE Combination -- 15.4.1 Associative Search -- 15.4.2 Adaptive Critic -- 15.4.3 The Cart-Pole System -- 15.5 Reinforcement Learning Versus Optimal Control.

Question Bank -- References -- Chapter 16. Neural Networks Applications -- 16.1 Introduction -- 16.2 Robot Control -- 16.2.1 Forward Kinematics -- 16.2.2 Inverse Kinematics -- 16.2.3 Dynamics -- 16.2.4 Trajectory Generation -- 16.2.5 End-Effector Positioning -- 16.2.5a Involvement of Neural Networks -- 16.2.6 Camera-Robot Coordination in Function Approximation -- 16.2.6a Approach-1: Feed-Forward Networks -- 16.2.6b Approach 2: Topology Conserving Maps -- 16.2.7 Robot Arm Dynamics -- 16.3 Detection of Tool Breakage in Milling Operations -- 16.3.1 Unsupervised Adaptive Resonance Theory (ART) Neural Networks -- 16.3.2 Results and Discussion -- Question Bank -- References -- Chapter 17 Hybrid Fuzzy Neural Networks -- 17.1 Introduction -- 17.2 Hybrid Systems -- 17.2.1 Sequential Hybrid Systems -- 17.2.2 Auxiliary Hybrid Systems -- 17.2.3 Embedded Hybrid Systems -- 17.3 Fuzzy Logic in Learning Algorithms -- 17.4 Fuzzy Neurons -- 17.5 Neural Networks as Pre-Processors or Post-Processors -- 17.6 Neural Networks as Tuners of Fuzzy Logic Systems -- 17.7 Advantages and Drawbacks of Neurofuzzy Systems -- 17.8 Commitee of Networks -- 17.9 FNN Architecture Based on Back Propagation -- 17.9.1 Strong L-R Representation of Fuzzy Numbers -- 17.9.2 Simulation -- 17.10 Adaptive Neuro-Fuzzy Inference System (ANFIS) -- 17.101 ANFIS Structure -- Question Bank -- References -- Chapter 18. Hybrid Fuzzy Neural Networks Applications -- 18.1 Introduction -- 18.2 Tool Breakage Monitoring System for End Milling -- 18.2.1 Methodology: Force Signals in the End Milling Cutting Process -- 18.2.2 Neural Networks -- 18.2.3 Experimental Design and System Development Experimental Design -- 18.2.4 Neural Network-BP System Development -- 18.2.5 Finding and Conclusions -- 18.3 Control of Combustion -- 18.3.1 Adaptive Neuro-Fuzzy Inference System -- 18.3.2 Learning Method of ANFIS.

18.3.3 Model of Combustion.