Riassunto
With existent uses ranging from motion detection to music synthesis to financial forecasting, recurrent neural networks have generated widespread attention. The tremendous interest in these networks drives Recurrent Neural Networks: Design and Applications, a summary of the design, applications, current research, and challenges of this subfield of artificial neural networks. This overview incorporates every aspect of recurrent neural networks. It outlines the wide variety of complex learning techniques and associated research projects. Each chapter addresses architectures, from fully connected to partially connected, including recurrent multilayer feedforward. It presents problems involving trajectories, control systems, and robotics, as well as RNN use in chaotic systems. The authors also share their expert knowledge of ideas for alternate designs and advances in theoretical aspects. The dynamical behavior of recurrent neural networks is useful for solving problems in science, engineering, and business. This approach will yield huge advances in the coming years. Recurrent Neural Networks illuminates the opportunities and provides you with a broad view of the current events in this rich field.
Contenuti
INTRODUCTION
Overview
Design Issues and Theory
Applications
Future Directions
RECURRENT NEURAL NETWORKS FOR OPTIMIZATION: THE STATE OF THE ART
Introduction
Continuous-Time Neural Networks for QP and LCP
Discrete-Time Neural Networks for QP and LCP
Simulation Results
Concluding Remarks
EFFICIENT SECOND-ORDER LEARNING ALGORITHMS FOR DISCRETE-TIME RECURRENT NEURAL NETWORKS
Introduction
Spatio x Spatio-Temporal Processing
Computational Capability
Recurrent Neural Networks as Nonlinear Dynamic Systems
Recurrent Neural Networks and Second-Order Learning Algorithms
Recurrent Neural Network Architectures
State Space Representation for Recurrent Neural Networks
Second Order Information in Optimization-Based Learning Algorithms
The Conjugate Gradient Algorithm
An Improved SGM Method
The Learning Algorithm for Recurrent Neural Networks
Simulation Results
Concluding Remarks
DESIGNING HIGH ORDER RECURRENT NETWORKS FOR BAYESIAN BELIEF REVISION
Introduction
Belief Revision and Reasoning Under Uncertainty
Hopfield Networks and Mean Field Annealing
High Order Recurrent Networks
Efficient Data Structures for Implementing HORNs
Designing HORNs for Belief Revision
Conclusions
EQUIVALENCE IN KNOWLEDGE REPRESENTATION: AUTOMATA, RECURRENT NEURAL NETWORKS, AND DYNAMICAL FUZZY SYSTEMS
Introduction
Fuzzy Finite State Automata
Representation of Fuzzy States
Automata Transformation
Network Architecture
Network Stability Analysis
Simulations
Conclusions
LEARNING LONG-TERM DEPENDENCIES IN NARX RECURRENT NEURAL NETWORKS
Introduction
Vanishing Gradients and Long-Term Dependencies
NARX Networks
An Intuitive Explanation of NARX Network Behavior
Experimental Results
Conclusion
OSCILLATION RESPONSES IN A CHAOTIC RECURRENT NETWORK
Introduction
Progression to Chaos
External Patterns
Dynamic Adjustment of Pattern Strength
Characteristics of the Pattern-to-Oscillation Map
Discussion
LESSON FROM LANGUAGE LEARNING
Introduction
Lesson 1: Language Learning is Hard
Lesson 2: When Possible, Search a Smaller Space
Lesson 3: Search the most Likely Places First
Lesson 4: Order your Training Data
Summary
RECURRENT AUTOASSOCIATIVE NETWORKS: DEVELOPING DISTRIBUTED REPRESENTATIONS OF STRUCTURED SEQUENCES BY AUTOASSOCIATION
Introduction
Sequences, Hierarchy, and Representations
Neural Networks and Sequential Processing
Recurrent Autoassociative Networks
A Cascade of RANs
Going Further to a Cognitive Model
Discussion
Conclusions
COMPARISON OF RECURRENT NEURAL NETWORKS FOR TRAJECTORY GENERATION
Introduction
Architecture
Training Set
Error Function and Performance Metric
Training Algorithms
Simulations
Conclusions
TRAINING ALGORITHMS FOR RECURRENT NEURAL NETS THAT ELIMINATE THE NEED FOR COMPUTATION OF ERROR GRADIENTS WITH APPLICATION TO TRAJECTORY PRODUCTION PROBLEM
Introduction
Description of the Learning Problem and some Issues in Spatiotemporal Training
Training by Methods of Learning Automata
Training by Simplex Optimization Method
Conclusions
TRAINING RECURRENT NEURAL NETWORKS FOR FILTERING AND CONTROL
Introduction
Preliminaries
Principles of Dynamic Learning
Dynamic Backprop for the LDRN
Neurocontrol Application
Recurrent Filter
Summary
REMEMBERING HOW TO BEHAVE: RECURRENT NEURAL NETWORKS FOR ADAPTIVE ROBOT BEHAVIOR
Introduction
Background
Recurrent Neural Networks for Adaptive Robot Behavior
Summary and Discussion
Le informazioni nella sezione "Su questo libro" possono far riferimento a edizioni diverse di questo titolo.
