{"product_id":"a-field-guide-to-dynamical-recurrent-networks-9780780353695","title":"A Field Guide to Dynamical Recurrent Networks","description":"\u003cb\u003eBook Synopsis\u003c\/b\u003e\u003cbr\u003eAcquire the tools for understanding new architectures and algorithms of dynamical recurrent networks (DRNs) from this valuable field guide, which documents recent forays into artificial intelligence, control theory, and connectionism. This unbiased introduction to DRNs and their application to time-series problems (such as classification and prediction) provides a comprehensive overview of the recent explosion of leading research in this prolific field.  \u003cp\u003e\u003ci\u003eA Field Guide to Dynamical Recurrent Networks\u003c\/i\u003e emphasizes the issues driving the development of this class of network structures. It provides a solid foundation in DRN systems theory and practice using consistent notation and terminology. Theoretical presentations are supplemented with applications ranging from cognitive modeling to financial forecasting.\u003c\/p\u003e \u003cp\u003e\u003ci\u003eA Field Guide to Dynamical Recurrent Networks\u003c\/i\u003e will enable engineers, research scientists, academics, and graduate students to apply DRNs to various real-world p\u003cbr\u003e\u003cbr\u003e\u003cb\u003eTable of Contents\u003c\/b\u003e\u003cbr\u003e\u003c\/p\u003e\u003cp\u003ePreface xvii\u003c\/p\u003e \u003cp\u003eAcknowledgments xix\u003c\/p\u003e \u003cp\u003eList of Figures xxi\u003c\/p\u003e \u003cp\u003eList of Tables xxvii\u003c\/p\u003e \u003cp\u003eList of Contributors xxix\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePART I INTRODUCTION 1\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 1 Dynamical Recurrent Networks 3\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eJohn F, Kolen and Stefan C. Kroner\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e1.1 Introduction 3\u003c\/p\u003e \u003cp\u003e1.2 Dynamical Recurrent Networks 4\u003c\/p\u003e \u003cp\u003e1.3 Overview 6\u003c\/p\u003e \u003cp\u003e1.4 Conclusion 11\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePART II ARCHITECTURES 13\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 2 Networks with Adaptive State Transitions 15\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eDavid Calvert and Stefan C. Kremer\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e2.1 Introduction 15\u003c\/p\u003e \u003cp\u003e2.2 The Search for Context 15\u003c\/p\u003e \u003cp\u003e2.3 Recurrent Approaches to Context 17\u003c\/p\u003e \u003cp\u003e2.4 Representing Context 18\u003c\/p\u003e \u003cp\u003e2.5 Training 19\u003c\/p\u003e \u003cp\u003e2.6 Architectures 19\u003c\/p\u003e \u003cp\u003e2.7 Conclusion 25\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 3 Delay Networks: Buffers to the Rescue 27\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eTsung-Nan Lin and C. Lee Giles\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e3.1 Introduction to Delay Networks 27\u003c\/p\u003e \u003cp\u003e3.2 Back-Propagation Through Time Learning Algorithm 28\u003c\/p\u003e \u003cp\u003e3.3 Delay Networks with Feedback: NARX Networks 31\u003c\/p\u003e \u003cp\u003e3.4 Long-Term Dependencies in NARX Networks 33\u003c\/p\u003e \u003cp\u003e3.5 Experimental Results: The Latching Problem 36\u003c\/p\u003e \u003cp\u003e3.6 Conclusion 38\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 4 Memory Kernels 39\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eAh Chung Tsoi, Andrew Back, Jose Principe, and Mike Mozer\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e4.1 Introduction 39\u003c\/p\u003e \u003cp\u003e4.2 Different Types of Memory Kernels 40\u003c\/p\u003e \u003cp\u003e4.3 Generic Representation of a Memory Kernel 44\u003c\/p\u003e \u003cp\u003e4.4 Basis Issues 45\u003c\/p\u003e \u003cp\u003e4.5 Universal Approximation Theorem 47\u003c\/p\u003e \u003cp\u003e4.6 Training Algorithms 48\u003c\/p\u003e \u003cp\u003e4.7 Illustrative Example 51\u003c\/p\u003e \u003cp\u003e4.8 Conclusion 54\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePART III CAPABILITIES 55\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 5 Dynamical Systems and Iterated Function Systems 57\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eJohn F. Kolen\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e5.1 Introduction 57\u003c\/p\u003e \u003cp\u003e5.2 Dynamical Systems 57\u003c\/p\u003e \u003cp\u003e5.3 Iterated Function Systems 72\u003c\/p\u003e \u003cp\u003e5.4 Symbolic Dynamics 78\u003c\/p\u003e \u003cp\u003e5.5 The DRN Connection 80\u003c\/p\u003e \u003cp\u003e5.6 Conclusion 81\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 6 Representation of Discrete States 83\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eC. Lee Giles and Christian Omlin\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e6.1 Introduction 83\u003c\/p\u003e \u003cp\u003e6.2 Finite-State Automata 83\u003c\/p\u003e \u003cp\u003e6.3 Neural Network Representations of DFA 85\u003c\/p\u003e \u003cp\u003e6.4 Pushdown Automata 99\u003c\/p\u003e \u003cp\u003e6.5 Turing Machines 101\u003c\/p\u003e \u003cp\u003e6.6 Conclusion 102\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 7 Simple Stable Encodings of Finite-State Machines in Dynamic Recurrent Networks 103\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eMikel L. Forcada and Raphael C. Carrasco\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e7.1 Introduction 103\u003c\/p\u003e \u003cp\u003e7.2 Definitions 106\u003c\/p\u003e \u003cp\u003e7.3 Encoding 109\u003c\/p\u003e \u003cp\u003e7.4 Encoding of Mealy Machines in DRN 114\u003c\/p\u003e \u003cp\u003e7.5 Encoding of Moore Machines in DRN 123\u003c\/p\u003e \u003cp\u003e7.6 Encoding of Deterministic Finite-State Automata in DRN 125\u003c\/p\u003e \u003cp\u003e7.7 Conclusion 126\u003c\/p\u003e \u003cp\u003e7.8 Acknowledgments 127\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 8 Representation Beyond Finite States: Alternatives to Pushdown Automata 129\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eJanet Wiles, Alan D. Blair, and Mikael Boden\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e8.1 Introduction 129\u003c\/p\u003e \u003cp\u003e8.2 Hierarchies of Languages and Machines 130\u003c\/p\u003e \u003cp\u003e8.3 DRNs and Nonregular Languages 134\u003c\/p\u003e \u003cp\u003e8.4 Generalization and Inductive Bias 141\u003c\/p\u003e \u003cp\u003e8.5 Conclusion 142\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 9 Universal Computation and Super-Hiring Capabilities 143\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eHava T. Siegelmann\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e9.1 Introduction 143\u003c\/p\u003e \u003cp\u003e9.2 The Model 144\u003c\/p\u003e \u003cp\u003e9.3 Preliminary: Computational Complexity 145\u003c\/p\u003e \u003cp\u003e9.4 Summary of Results 146\u003c\/p\u003e \u003cp\u003e9.5 Pondering Real Weights 149\u003c\/p\u003e \u003cp\u003e9.6 Analog Computation 149\u003c\/p\u003e \u003cp\u003e9.7 Conclusion 150\u003c\/p\u003e \u003cp\u003e9.7 Acknowledgments 151\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePART IV ALGORITHMS 153\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 10 Insertion of Prior Knowledge 155\u003c\/b\u003e\u003cbr\u003e\u003ci\u003ePaolo Frasconi, C. Lee Giles, Marco Gori, and Christian Omlin\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e10.1 Introduction 155\u003c\/p\u003e \u003cp\u003e10.2 Constrained Nondeterministic Insertion in First-Order Networks 156\u003c\/p\u003e \u003cp\u003e10.3 Second-Order Networks 160\u003c\/p\u003e \u003cp\u003e10.4 Other Related Techniques 175\u003c\/p\u003e \u003cp\u003e10.5 Conclusion 177\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 11 Gradient Calculations for Dynamic Recurrent Neural Networks 179\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eBarak A. Pearlmutter\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e11.1 Introduction 179\u003c\/p\u003e \u003cp\u003e11.2 Learning in Networks with Fixed Points 182\u003c\/p\u003e \u003cp\u003e11.3 Computing the Gradient Without Assuming a Fixed Point 188\u003c\/p\u003e \u003cp\u003e11.4 Some Simulations 196\u003c\/p\u003e \u003cp\u003e11.5 Stability and Perturbation Experiments 198\u003c\/p\u003e \u003cp\u003e11.6 Other Non-Fixed Point-Techniques 199\u003c\/p\u003e \u003cp\u003e11.7 Learning with Scale Parameters 203\u003c\/p\u003e \u003cp\u003e11.8 Conclusion 203\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 12 Understanding and Explaining DRN Behavior 207\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eChristian Omlin\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e12.1 Introduction 207\u003c\/p\u003e \u003cp\u003e12.2 Performance Deterioration 208\u003c\/p\u003e \u003cp\u003e12.3 Dynamic Space Exploration 209\u003c\/p\u003e \u003cp\u003e12.4 DFA Extraction: Fool's Gold? 215\u003c\/p\u003e \u003cp\u003e12.5 Theoretical Foundations 216\u003c\/p\u003e \u003cp\u003e12.6 How Can DFA Outperform Networks? 218\u003c\/p\u003e \u003cp\u003e12.7 Alternative Extraction Methods 220\u003c\/p\u003e \u003cp\u003e12.8 Extension to Fuzzy Automata 225\u003c\/p\u003e \u003cp\u003e12.9 Application to Financial Forecasting 226\u003c\/p\u003e \u003cp\u003e12.10 Conclusion 227\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePART V LIMITATIONS 229\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 13 Evaluating Benchmark Problems by Random Guessing 231\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eJiirgen Schmidhuber, Sepp Hochreiter, and Yoshua Bengio\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e13.1 Introduction 231\u003c\/p\u003e \u003cp\u003e13.2 Random Guessing (RG) 231\u003c\/p\u003e \u003cp\u003e13.3 Experiments 232\u003c\/p\u003e \u003cp\u003e13.4 Final Remarks 234\u003c\/p\u003e \u003cp\u003e13.5 Conclusion 235\u003c\/p\u003e \u003cp\u003e13.6 Acknowledgments 235\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 14 Gradient Flow in Recurrent Nets: The Difficulty of Learning Long-Term Dependencies 237\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eSepp Hochreiter, Yoshua Bengio, Paolo Frasconi, and Jiirgen Schmidhuber\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e14.1 Introduction 237\u003c\/p\u003e \u003cp\u003e14.2 Exponential Error Decay 237\u003c\/p\u003e \u003cp\u003e14.3 Dilemma: Avoiding Aradient Decay Prevents Long-Term Latching 240\u003c\/p\u003e \u003cp\u003e14.4 Remedies 241\u003c\/p\u003e \u003cp\u003e14.5 Conclusion 243\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 15 Limiting the Computational Power of Recurrent Neural Networks: VC Dimension and Noise 245\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eChristopher Moore\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e15.1 Introduction 245\u003c\/p\u003e \u003cp\u003e15.2 Time-Bounded Networks and VC Dimension 246\u003c\/p\u003e \u003cp\u003e15.3 Robustness to Noise 250\u003c\/p\u003e \u003cp\u003e15.4 Conclusion 254\u003c\/p\u003e \u003cp\u003e15.5 Acknowledgments 254\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePART VI APPLICATIONS 255\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 16 Dynamical Recurrent Networks in Control 257\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eDanil V Prokhorov, Gintaras V Puskorius, and Lee A. Feldkamp\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e16.1 Introduction 257\u003c\/p\u003e \u003cp\u003e16.2 Description and Execution of TLRNN 258\u003c\/p\u003e \u003cp\u003e16.3 Elements of Training 260\u003c\/p\u003e \u003cp\u003e16.4 Basic Approach to Controller Synthesis 266\u003c\/p\u003e \u003cp\u003e16.5 Example 1 272\u003c\/p\u003e \u003cp\u003e16.6 Example 2 282\u003c\/p\u003e \u003cp\u003e16.7 Conclusion 288\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 17 Sentence Processing and Linguistic Structure 291\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eWhitney Tabor\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e17.1 Introduction 291\u003c\/p\u003e \u003cp\u003e17.2 Case Studies: Dynamical Networks for Sentence Processing 295\u003c\/p\u003e \u003cp\u003e17.3 Conclusion 308\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 18 Neural Network Architectures for the Modeling of Dynamic Systems 311\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eHans-Georg Zimmermann and Ralph Neuneier\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e18.1 Introduction and Overview 311\u003c\/p\u003e \u003cp\u003e18.2 Modeling Dynamic Systems by Feedforward Neural Networks 312\u003c\/p\u003e \u003cp\u003e18.3 Modeling Dynamic Systems by Recurrent Neural Networks 321\u003c\/p\u003e \u003cp\u003e18.4 Combining State-Space Reconstruction and Forecasting 334\u003c\/p\u003e \u003cp\u003e18.5 Conclusion 350\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 19 From Sequences to Data Structures: Theory and Applications 351\u003c\/b\u003e\u003cbr\u003e\u003ci\u003ePaolo Frasconi, Marco Gori, Andreas Kuchler, and Alessandro Sperduti\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e19.1 Introduction 351\u003c\/p\u003e \u003cp\u003e19.2 Historical Remarks 352\u003c\/p\u003e \u003cp\u003e19.3 Adaptive Processing of Structured Information 354\u003c\/p\u003e \u003cp\u003e19.4 Applications 366\u003c\/p\u003e \u003cp\u003e19.5 Conclusion 374\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePART VII CONCLUSION 375\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 20 Dynamical Recurrent Networks: Looking Back and Looking Forward 377\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eStefan C. Kremer and John F. Kolen\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e20.1 Introduction 377\u003c\/p\u003e \u003cp\u003e20.2 The Challenges 377\u003c\/p\u003e \u003cp\u003e20.3 The Potential 378\u003c\/p\u003e \u003cp\u003e20.4 The Approaches 378\u003c\/p\u003e \u003cp\u003e20.5 The Successes 378\u003c\/p\u003e \u003cp\u003e20.6 Conclusion 378\u003c\/p\u003e \u003cp\u003eBibliography 379\u003c\/p\u003e \u003cp\u003eGlossary 409\u003c\/p\u003e \u003cp\u003eIndex 415\u003c\/p\u003e \u003cp\u003eAbout the Editors 423\u003c\/p\u003e","brand":"John Wiley \u0026 Sons Inc","offers":[{"title":"Default Title","offer_id":49404990914903,"sku":"9780780353695","price":173.66,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0817\/1739\/5799\/files\/9780780353695.jpg?v=1730488299","url":"https:\/\/bookcurl.com\/products\/a-field-guide-to-dynamical-recurrent-networks-9780780353695","provider":"Book Curl","version":"1.0","type":"link"}