You are previewing Artificial Higher Order Neural Networks for Modeling and Simulation.
O'Reilly logo
Artificial Higher Order Neural Networks for Modeling and Simulation

Book Description

With artificial neural network research being one of the new directions for new generation computers, current research suggests that open-box artificial higher order neural networks (HONNs) play an important role in this new direction. Artificial Higher Order Neural Networks for Modeling and Simulation introduces artificial Higher Order Neural Networks (HONNs) to professionals working in the fields of modeling and simulation, and explains that HONN is an open-box artificial neural network tool as compared to traditional artificial neural networks. Including details of the most popular HONN models, this book provides an opportunity for practitioners in the field of modeling and simulations to understand and know how to use HONNS in their area of expertise.

Table of Contents

  1. Cover
  2. Title Page
  3. Copyright Page
  4. Editorial Advisory Board and List of Reviewers
    1. EDITORIAL ADVISORY BOARD
    2. LIST OF REVIEWERS
  5. Dedication
  6. Preface
  7. Acknowledgment
  8. Section 1: Artificial Higher Order Neural Networks for Modeling
    1. Chapter 1: Artificial Multi-Polynomial Higher Order Neural Network Models
      1. ABSTRACT
      2. INTRODUCTION
      3. HIGHER ORDER NEURAL NETWORKS
      4. MULTI-POLYNOMIAL HIGHER ORDER NEURAL NETWORK MODEL (MPHONN)
      5. APPLICATIONS OF MPHONN
      6. FUTURE RESEARCH DIRECTIONS
      7. CONCLUSION
    2. Chapter 2: Artificial Higher Order Neural Networks for Modeling MIMO Discrete-Time Nonlinear System
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. NEURAL IDENTIFICATION
      5. APPLICATION
      6. FUTURE RESEARCH DIRECTIONS
      7. CONCLUSION
    3. Chapter 3: Artificial Higher Order Neural Networks for Modeling Combinatorial Optimization Problems
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. HIGH-ORDER DISCRETE HOPFIELD NETWORK
      4. 3. HIGH ORDER NETWORK MODELING COMBINATORIAL OPTIMIZATION PROBLEM
      5. 4. SUMMARY
    4. Chapter 4: Needle Insertion Force Modeling using Genetic Programming Polynomial Higher Order Neural Network
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. SOFT TISSUE INSERTION METHODS AND FORMULATION
      4. 3. EXPERIMENTAL SETUP FOR SOFT TISSUE NEEDLE INSERTION
      5. 4. GENETIC-BASED POLYNOMIAL HIGHER ORDER NEURAL NETWORK
      6. 5. RESULTS
      7. 6. DISCUSSION
      8. 7. CONCLUSION AND FUTURE WORK
  9. Section 2: Artificial Higher Order Neural Networks for Simulation
    1. Chapter 5: Artificial Polynomial and Trigonometric Higher Order Neural Network Group Models
      1. ABSTRACT
      2. INTRODUCTION
      3. PHONNG GROUP
      4. TRIGONOMETRIC POLYNOMIAL HIGHER ORDER NEURAL NETWORK GROUPS
      5. HIGHER ORDER NEURAL NETWORK GROUP FINANCIAL SIMULATION SYSTEM
      6. PRELIMINARY TESTING OF PHONNG AND THONNG SIMULATOR
      7. FUTURE RESEARCH DIRECTIONS
      8. CONCLUSION
    2. Chapter 6: Fundamentals of Higher Order Neural Networks for Modeling and Simulation
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. SECOND ORDER NEURAL UNITS AND SECOND ORDER NEURAL NETWORKS
      4. 3. PERFORMANCE ASSESSMENT OF SECOND ORDER NEURAL UNITS
      5. 4. HIGHER ORDER NEURAL UNITS AND HIGHER ORDER NEURAL NETWORKS
      6. 5. ENGINEERING APPLICATIONS
      7. 6. CONCLUDING REMARKS AND FUTURE RESEARCH DIRECTIONS
    3. Chapter 7: High Order Neuro-Fuzzy Dynamic Regulation of General Nonlinear Multi-Variable Systems
      1. ABSTRACT
      2. INTRODUCTION
      3. PROBLEM FORMULATION AND NEURO-FUZZY APPROXIMATION
      4. STABILITY ANALYSIS
      5. CONCLUSION
      6. FUTURE TRENDS
    4. Chapter 8: Modeling and Simulation of Alternative Energy Generation Processes using HONN
      1. ABSTRACT
      2. INTRODUCTION
      3. HIGHER ORDER NEURAL NETWORKS
      4. BIOMETHANE GENERATION PROCESS
      5. HYDROGEN GENERATION PROCESS
      6. FUTURE RESEARCH DIRECTIONS
      7. CONCLUSION
  10. Section 3: Artificial Higher Order Neural Networks for Control and Predication
    1. Chapter 9: Distributed Adaptive Control for Multi-Agent Systems with Pseudo Higher Order Neural Net
      1. ABSTRACT
      2. INTRODUCTION
      3. NEURAL NET AND FUNCTION APPROXIMATION
      4. SYNCHRONIZATION CONTROL FORMULATION
      5. LYAPUNOV DESIGN FOR NETWORKED SYSTEMS: DISTRIBUTED NN TUNING PROTOCOLS
      6. SIMULATION RESULTS
      7. CONCLUSION
    2. Chapter 10: Cooperative Control of Unknown Networked Lagrange Systems using Higher Order Neural Networks
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. PRELIMINARIES
      5. DISTRIBUTED ADAPTIVE CONTROLLER DESIGN
      6. ROBUST DISTRIBUTED CONTROLLER DESIGN
      7. ILLUSTRATIVE DESIGN AND SIMULATION
      8. CONCLUSION
    3. Chapter 11: Symbolic Function Network
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. OVERVIEW OF SFN MODEL
      5. MPEG VIDEO CODED TRAFFIC PREDICTION
      6. PACKET LOSS RATIO PREDICTION
      7. PREDICTION OF ROUND TRIP TIME (RTT)
      8. FUTURE RESEARCH DIRECTIONS
      9. CONCLUSION
    4. Chapter 12: Time Series Forecasting via a Higher Order Neural Network trained with the Extended Kalman Filter for Smart Grid Applications
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. MATHEMATICAL PRELIMINARIES
      4. 3. FORECASTING PROBLEM IN WIND GENERATION SYSTEMS
      5. 4. NEURAL NETWORK DESIGN
      6. 5. LEARNING ALGORITHM BASED ON EKF
      7. 6. SIMULATION RESULTS
      8. 7. FUTURE RESEARCH DIRECTIONS
      9. 8. CONCLUSION
  11. Section 4: Artificial Higher Order Neural Network Models and Applications
    1. Chapter 13: HONNs with Extreme Learning Machine to Handle Incomplete Datasets
      1. ABSTRACT
      2. INTRODUCTION
      3. ELM ALGORITHM
      4. HONN MODELS WITH ELM ALGORITHM
      5. HONN MODEL APPLICATIONS
      6. CONCLUSION
    2. Chapter 14: Symbolic Function Network
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. BACKGROUND
      4. 3. SFN MODEL
      5. 4. SFN OPTIMIZATION
      6. 5. ILLUSTRATIVE EXAMPLES
      7. 6. CONCLUSION
    3. Chapter 15: City Manager Compensation and Performance
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. BACKGROUND: NEURAL NETWORK IN ACCOUNTING RESEARCH
      4. 3. DATA AND SAMPLE SELECTION
      5. 4. RESULTS AND ANALYSIS
      6. 5. CONCLUSION
      7. 6. FUTURE RESEARCH DIRECTIONS
    4. Chapter 16: On Some Dynamical Properties of Randomly Connected Higher Order Neural Networks
      1. ABSTRACT
      2. INTRODUCTION
      3. RANDOMLY CONNECTED HIGHER ORDER NEURAL NETWORKS
      4. TRANSFORMATION AND STABILITY OF THE NETWORKS
      5. DYNAMICS OF GROUPS OF RHONNS
      6. CONCLUSION
      7. APPENDIX
    5. Chapter 17: A Hybrid Higher Order Neural Structure for Pattern Recognition
      1. ABSTRACT
      2. INTRODUCTION
      3. HIGHER ORDER NEURAL NETWORK STRUCTURES AND MODELS
      4. STRUCTURE AND LEARNING ALGORITHM OF HYBRID HIGHER ORDER NEURAL NETWORK
      5. HHONC: EXPERIMENTAL RESULTS
      6. HHONN: EXPERIMENTAL RESULTS
      7. CONCLUSION
  12. Compilation of References
  13. About the Contributors