You are previewing Applied Artificial Higher Order Neural Networks for Control and Recognition.
O'Reilly logo
Applied Artificial Higher Order Neural Networks for Control and Recognition

Book Description

In recent years, Higher Order Neural Networks (HONNs) have been widely adopted by researchers for applications in control signal generating, pattern recognition, nonlinear recognition, classification, and predition of control and recognition scenarios. Due to the fact that HONNs have been proven to be faster, more accurate, and easier to explain than traditional neural networks, their applications are limitless. Applied Artificial Higher Order Neural Networks for Control and Recognition explores the ways in which higher order neural networks are being integrated specifically for intelligent technology applications. Emphasizing emerging research, practice, and real-world implementation, this timely reference publication is an essential reference source for researchers, IT professionals, and graduate-level computer science and engineering students.

Table of Contents

  1. Cover
  2. Title Page
  3. Copyright Page
  4. Book Series
    1. Mission
    2. Coverage
  5. Dedication
  6. Editorial Advisory Board
  7. Preface
  8. Acknowledgment
  9. Section 1: Artificial Higher Order Neural Networks for Control
    1. Chapter 1: Ultra High Frequency Polynomial and Trigonometric Higher Order Neural Networks for Control Signal Generator
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. UPT-HONN MODELS
      5. LEARNING ALGORITHM OF UPT-HONN MODELS
      6. UPT-HONN TESTING
      7. FUTHER RESEARCH DIRECTIONS
      8. CONCLUSION
      9. REFERENCES
    2. Chapter 2: HONU and Supervised Learning Algorithms in Adaptive Feedback Control
      1. ABSTRACT
      2. INTRODUCTION
      3. HIGHER ORDER NEURAL UNITS
      4. NOISE EFFECT ON ADAPTIVE PLANT IDENTIFICATION
      5. HONU AS AN ADAPTIVE FEEDBACK
      6. CONCLUSION
      7. REFERENCES
    3. Chapter 3: Novelty Detection in System Monitoring and Control with HONU
      1. ABSTRACT
      2. INTRODUCTION
      3. HONU AS PLANT OR CLOSED LOOP ADAPTIVE MODEL
      4. NOVELTY DETECTION TECHNIQUES WITH HONU
      5. ADAPTIVE NOVELTY DETECTION WITH LEAST-SQUARES METHODS
      6. SUMMARY
      7. REFERENCES
  10. Section 2: Artificial Higher Order Neural Networks for Recognition
    1. Chapter 4: Ultra High Frequency Sigmoid and Trigonometric Higher Order Neural Networks for Data Pattern Recognition
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. UGT-HONN MODELS
      5. LEARNING ALGORITHM OF UGT-HONN MODELS
      6. UGT-HONN TESTING
      7. CONCLUSION
      8. REFERENCES
    2. Chapter 5: Ultra High Frequency SINC and Trigonometric Higher Order Neural Networks for Data Classification
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. UNT-HONN MODELS
      5. LEARNING ALGORITHM OF UPT-HONN MODELS
      6. FUTURE RESEARCH DIRECTIONS
      7. CONCLUSION
      8. REFERENCES
    3. Chapter 6: Integration of Higher-Order Time-Frequency Statistics and Neural Networks
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. INTEGRATION OF HOS AND ANN
      5. PROPOSED METHODOLOGY: THE HOS-BASED ANN
      6. RESULTS
      7. FUTURE RESEARCH DIRECTIONS
      8. CONCLUSION
      9. ACKNOWLEDGMENT
      10. REFERENCES
      11. KEY TERMS AND DEFINITIONS
      12. APPENDIX
  11. Section 3: Artificial Higher Order Neural Networks for Simulation and Predication
    1. Chapter 7: Adaptive Hybrid Higher Order Neural Networks for Prediction of Stock Market Behavior
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. RELATED STUDIES TO HONN
      4. 3. ADAPTIVE HONN BASED FORECASTING MODELS
      5. 4. SIMULATION RESULTS AND ANALYSIS
      6. 5. CONCLUSION AND FURTHER RESEARCH
      7. REFERENCES
    2. Chapter 8: Theoretical Analyses of the Universal Approximation Capability of a class of Higher Order Neural Networks based on Approximate Identity
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. SOME NOTATIONS AND BASIC DEFINITIONS
      4. 3 THEORETICAL ANALYSES IN THE SPACE OF CONTINUOUS MULTIVARIATE FUNCTIONS
      5. 4. THEORETICAL ANALYSES IN THE SPACE OF LEBESGUE INTEGRABLE MULTIVARIATE FUNCTIONS
      6. 5. CONCLUSION
      7. ACKNOWLEDGMENT
      8. REFERENCES
    3. Chapter 9: Artificial Sine and Cosine Trigonometric Higher Order Neural Networks for Financial Data Prediction
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. SIN-HONN AND COS-HONN MODELS
      5. LEARNING ALGORITHM OF SIN-HONN AND COS-HONN MODELS
      6. FINANCIAL DATA PREDICTION USING HONN MODELS
      7. FUTURE RESEARCH DIRECTIONS
      8. CONCLUSION
      9. REFERENCES
    4. Chapter 10: Cosine and Sigmoid Higher Order Neural Networks for Data Simulations
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. MODELS OF CS-HONN
      5. CS-HONN TIME SERIES ANALYSIS SYSTEM
      6. LEARNING ALGORITHM OF CS-HONN
      7. TIME SERIES DATA TEST USING CS-HONN
      8. FUTURE RESEARCH DIRECTIONS
      9. CONCLUSION
      10. REFERENCES
    5. Chapter 11: Improving Performance of Higher Order Neural Network using Artificial Chemical Reaction Optimization
      1. ABSTRACT
      2. INTRODUCTION
      3. 1. HIGHER ORDER NEURAL NETWORK (HONN)
      4. 2. ARTIFICIAL CHEMICAL REACTION OPTIMIZATION (ACRO)
      5. 3. STOCK MARKET FORECASTING
      6. 4. ACRO BASED FLN FOR STOCK MARKET FORECASTING
      7. 5. SIMULATION RESULTS AND PERFORMANCE ANALYSIS
      8. 6. CONCLUSION
      9. REFERENCES
  12. Section 4: Artificial Higher Order Neural Network Models and Applications
    1. Chapter 12: Artificial Higher Order Neural Network Models
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. HIGHER ORDER NEURAL NETWORK ARCHITECTURE AND MODELS
      5. GENERAL LEARNING ALGORITHM AND WEIGHT UPDATE FORMULAE
      6. 24 HONN MODELS LEARNING ALGORITHM AND WEIGHT UPDATE FORMULAE
      7. FUTURE RESEARCH DIRECTIONS
      8. CONCLUSION
      9. REFERENCES
    2. Chapter 13: A Theoretical Framework for Parallel Implementation of Deep Higher Order Neural Networks
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND AND LITERATURE REVIEW
      4. THEORETICAL FRAMEWORK
      5. SUMMARY AND FUTURE RESEARCH DIRECTIONS
      6. REFERENCES
      7. KEY TERMS AND DEFINITIONS
    3. Chapter 14: Ant Colony Optimization Applied to the Training of a High Order Neural Network with Adaptable Exponential Weights
      1. ABSTRACT
      2. 1. OVERVIEW
      3. 2. THE HONEST NEURAL NETWORK
      4. 3. THE ACO ALGORITHM
      5. 4. PROPOSAL
      6. 5. EXPERIMENTAL METHODOLOGY AND RESULTS
      7. 6. CONCLUDING REMARKS
      8. REFERENCES
    4. Chapter 15: Utilizing Feature Selection on Higher Order Neural Networks
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND OF HIGHER ORDER NEURAL NETWORK
      4. FEATURE SELECTION
      5. EXPERIMENTS
      6. FUTURE RESEARCH DIRECTIONS
      7. CONCLUSION
      8. ACKNOWLEDGMENT
      9. REFERENCES
      10. KEY TERMS AND DEFINITIONS
    5. Chapter 16: Some Properties on the Capability of Associative Memory for Higher Order Neural Networks
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. HIGHER ORDER NEURONS
      4. 3. ASSOCIATIVE MEMORY FOR THE CONVENTIONAL NEURAL NETWORKS
      5. 4. ASSOCIATIVE CAPABILITIES FOR HONNs
      6. 5. HOMOGENEOUS NEURAL NETWORKS
      7. 6. CONCLUDING REMARKS AND FUTURE TREND
      8. REFERENCES
      9. APPENDIX
    6. Chapter 17: Discrete-Time Decentralized Inverse Optimal Higher Order Neural Network Control for a Multi-Agent Omnidirectional Mobile Robot
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. INVERSE OPTIMAL CONTROL: A CLF APPROACH
      5. NEURAL IDENTIFICATION
      6. THE EKF TRAINING ALGORITHM
      7. KUKA YOUBOT APPLICATION
      8. SIMULATION RESULTS
      9. CONCLUSION
      10. REFERENCES
    7. Chapter 18: Higher Order Neural Network for Financial Modeling and Simulation
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. PRELIMINARIES
      4. 3. PSO-FLANN AS HONN FOR FINANCIAL MODELING
      5. 4. EXPERIMENTAL DETAILS
      6. 5. CONCLUSION AND FUTURE RESEARCH DIRECTIONS
      7. REFERENCES
  13. Compilation of References
  14. About the Contributors