You are previewing System and Circuit Design for Biologically-Inspired Intelligent Learning.
O'Reilly logo
System and Circuit Design for Biologically-Inspired Intelligent Learning

Book Description

Despite significant research and studies in biologically-inspired circuit design, the capability of the biological creatures still excels that of artificially human-made systems inspired in terms of adaptivity, sensitivity, and spectral characteristics. System and Circuit Design for Biologically-Inspired Intelligent Learning aims to bridge that gap in the belief that compact organization and arrangement of the circuit and system design will be a major factor in attaining the pursued benefits of biological systems. Including research from abstract fields such as psychology to more concrete topics including circuit design, this text is designed for even fresh reader to make a smooth transition from principles to system/circuit architectures which simulate learning intelligence. 

Table of Contents

  1. Cover
  2. Title Page
  3. Copyright Page
  4. Editorial Advisory Board and List of Reviewers
    1. LIST OF REVIEWERS
  5. Preface
  6. Chapter 1: Biologically-Inspired Learning and Intelligent System Modeling
    1. ABSTRACT
    2. INTRODUCTION
    3. BACKGROUND
    4. CONCLUSION
  7. Chapter 2: Representation of Neuro-Information and Knowledge
    1. ABSTRACT
    2. INTRODUCTION
    3. BACKGROUND
    4. GROUNDED NATURE OF REPRESENTATION
    5. FUTURE RESEARCH DIRECTIONS
    6. CONCLUSION
  8. Chapter 3: Learning
    1. ABSTRACT
    2. INTRODUCTION
    3. BEHAVIORISM
    4. ASSOCIATIVE MECHANISMS OF LEARNING
    5. COGNITIVE MECHANISMS OF LEARNING
    6. VISUAL LEARNING
    7. FUTURE RESEARCH DIRECTIONS
    8. CONCLUSION
  9. Chapter 4: Biologically-Inspired Learning
    1. ABSTRACT
    2. INTRODUCTION
    3. BIOLOGICAL NEURAL NETWORKS
    4. COMPUTATION WITH ARTIFICIAL NEURAL NETWORKS
    5. FEED-FORWARD MULTI-LAYER PERCEPTRON
    6. SELF-ORGANIZING MAP NEURAL NETWORKS
    7. CONCLUSION
  10. Chapter 5: Optimality-Oriented Stabilization for Recurrent Neural Networks
    1. ABSTRACT
    2. INTRODUCTION
    3. PART-A: INPUT-TO-STATE STABILIZATION FOR DETERMINISTIC RECURRENT NEURAL NETWORKS
    4. PART-B: NOISE-TO-STATE STABILIZATION FOR STOCHASTIC RECURRENT NEURAL NETWORKS
    5. CONCLUSION
  11. Chapter 6: Design of Globally Robust Control for Biologically-Inspired Noisy Recurrent Neural Networks
    1. ABSTRACT
    2. INTRODUCTION
    3. PROBLEM FORMULATION
    4. GLOBAL ROBUST CONTROL DESIGN
    5. NUMERICAL EXAMPLES
    6. CONCLUSION
    7. APPENDIX
  12. Chapter 7: A Biologically Inspired Evolving Spiking Neural Model with Rank-Order Population Coding and a Taste Recognition System Case Study
    1. ABSTRACT
    2. INTRODUCTION
    3. BACKGROUND
    4. EVOLVING SPIKING NEURAL NETWORK WITH RANK ORDER POPULATION CODING
    5. CASE STUDY ON A BENCHMARK TASTE DATASET
    6. FUTURE RESEARCH DIRECTIONS
    7. CONCLUSION
  13. Chapter 8: Faster Self-Organizing Fuzzy Neural Network Training and Improved Autonomy with Time-Delayed Synapses for Locally Recurrent Learning
    1. ABSTRACT
    2. INTRODUCTION
    3. BACKGROUND
    4. HYBRID FUZZY NEURAL NETWORKS
    5. METHODOLOGY
    6. MODIFICATIONS TO THE SOFNN LEARNING ALGORITHM AND ARCHITECTURE
    7. RESULTS & DISCUSSION
    8. FUTURE RESEARCH DIRECTIONS
    9. CONCLUSION
  14. Chapter 9: Biologically-Inspired Learning and Intelligence
    1. ABSTRACT
    2. INTRODUCTION
    3. BASIC DEFINITIONS
    4. ANALOG FUZZIFIER IMPLEMENTATIONS
    5. A NEW COMPACT HIGH-PERFORMANCE LTA-MIN CIRCUIT
    6. A NEW CURRENT-MODE MEMBERSHIP FUNCTION CIRCUIT AND ITS APPLICATION TO FUZZY CLASSIFICATION
    7. CIRCUITS USING ALGEBRAIC FORMS FOR SIMILARITY ASSESSMENT
    8. CONCLUSION
  15. Chapter 10: A Biomimetic Adaptive Algorithm and Micropower Circuit Architecture for Implantable Neural Decoders
    1. ABSTRACT
    2. INTRODUCTION
    3. METHODS OF DESIGNING AND TESTING A MICROPOWER NEURAL DECODING SYSTEM
    4. EVALUATING THE PERFORMANCE OF THE NEURAL DECODING SYSTEM
    5. EVALUATING DESIGN TRADEOFFS IN THE CONSTRUCTION OF AN IMPLANTABLE NEURAL DECODER
    6. FUTURE RESEARCH DIRECTIONS
    7. CONCLUSION
  16. Chapter 11: FPGA Coprocessor for Simulation of Neural Networks Using Compressed Matrix Storage
    1. ABSTRACT
    2. INTRODUCTION
    3. UNSUPERVISED LEARNING USING BINARY NEURONS
    4. FPGA COPROCESSOR ARCHITECTURE
    5. DISCUSSION AND FUTURE RESEARCH
    6. Appendix A: Terms, Definitions and Parameters Used
  17. Chapter 12: Neural Network Circuits for Embedded Sensors Applications
    1. ABSTRACT
    2. INTRODUCTION
    3. BACKGROUND
    4. ANALOGUE NEURAL NETWORK CIRCUITS FOR LOW-POWER EMBEDDED SENSOR APPLICATIONS
    5. FUTURE RESEARCH DIRECTIONS
    6. CONCLUSION
  18. Chapter 13: Parallel Hardware for Artificial Neural Networks Using Fixed Floating Point Representation
    1. ABSTRACT
    2. INTRODUCTION
    3. ANNS COMPUTATIONAL MODEL
    4. APPROXIMATION OF THE OUTPUT FUNCTION
    5. IMPLEMENTATION ISSUES
    6. ANN HARDWARE ARCHITECTURE
    7. CONCLUSION
  19. Chapter 14: A Novel DCGA Optimization Technique for Guaranteed BIBO-Stable Frequency-Response Masking Digital Filters Incorporating Bilinear Lossless Discrete-integrator IIR Interpolation Sub-Filters
    1. ABSTRACT
    2. INTRODUCTION
    3. BACKGROUND
    4. FRM APPROACH
    5. CONSTRAINTS FOR GAURANTEED BIBO STABILITY
    6. GENERATION OF CSD LUTS
    7. FUTURE WORK
    8. CONCLUSION
  20. Chapter 15: Neuromodeling and Natural Optimization of Nonlinear Devices and Circuits
    1. ABSTRACT
    2. INTRODUCTION
    3. ARTIFICIAL NEURAL NETWORKS
    4. NATURAL OPTIMIZATION ALGORITHMS
    5. APPLICATIONS
    6. HYBRID EM-OPTIMIZATION METHOD FOR OPTIMAL DESIGN OF FSS
    7. CONCLUSION
  21. Compilation of References
  22. About the Contributors