Home : Book details : Book description

Description of  Recurrent Neural Networks

About the Book The concept of neural network originated from neuroscience, and one of its primitive aims is to help us understand the principle of the central nerve system and related behaviors through mathematical modeling. The first part of the book is a collection of three contributions dedicated to this aim. The second part of the book consists of seven chapters, all of which are about system identification and control. The third part of the book is composed of Chapter 11 and Chapter 12, where two interesting RNNs are discussed, respectively.The fourth part of the book comprises four chapters focusing on optimization problems. Doing optimization in a way like the central nerve systems of advanced animals including humans is promising from some viewpoints. Table of Contents 01 Aperiodic (Chaotic) Behavior in RNN with Homeostasis as a Source of Behavior Novelty: Theory and Applications 02 Biological Signals Identification by a Dynamic Recurrent Neural Network: from Oculomotor Neural Integrator to Complex Human Movements and Locomotion 03 Linguistic Productivity and Recurrent Neural Networks 04 Recurrent Neural Network Identification and Adaptive Neural Control of Hydrocarbon Biodegradation Processes 05 Design of Self-Constructing Recurrent-Neural-Network-Based Adaptive Control 06 Recurrent Fuzzy Neural Networks and Their Performance Analysis 07 Recurrent Interval Type-2 Fuzzy Neural Network Using Asymmetric Membership Functions 08 Rollover Control in Heavy Vehicles via Recurrent High Order Neural Networks 09 A New Supervised Learning Algorithm of Recurrent Neural Networks and L2 Stability Analysis in Discrete-Time Domain 10 Application of Recurrent Neural Networks to Rainfall-runoff Processes 11 Recurrent Neural Approach for Solving Several Types of Optimization Problems 12 Applications of Recurrent Neural Networks to Optimization Problems 13 Neurodynamic Optimization: Towards Nonconvexity 14 An Improved Extremum Seeking Algorithm Based on the Chaotic Annealing Recurrent Neural Network and Its Application 15 Stability Results for Uncertain Stochastic High-Order Hopfield Neural Networks with Time Varying Delays 16 Dynamics of Two-Dimensional Discrete-Time Delayed Hopfield Neural Networks 17 Case Studies for Applications of Elman Recurrent Neural Networks 18 Partially Connected Locally Recurrent Probabilistic Neural Networks