Research Catalog

Title

The roots of backpropagation : from ordered derivatives to neural networks and political forecasting / Paul John Werbos.

Author

Werbos, Paul J. (Paul John), 1947-

Publication

New York : Wiley, ©1994.

Items in the Library & Off-site

Details

Description

xii, 319 pages : illustrations; 25 cm.

Summary

• Scientists, engineers, statisticians, operations researchers, and other investigators involved in neural networks have long sought direct access to Paul Werbos's groundbreaking, much-cited 1974 Harvard doctoral thesis, The Roots of Backpropagation, which laid the foundation of backpropagation.
• Now, with the publication of its full text, these practitioners can go straight to the original material and gain a deeper, practical understanding of this unique mathematical approach to social studies and related fields. In addition, Werbos has provided three more recent research papers, which were inspired by his original work, and a new guide to the field.
• Originally written for readers who lacked any knowledge of neural nets, The Roots of Backpropagation firmly establishes both its historical and continuing significance as it demonstrates the ongoing value and new potential of backpropagation; creates a wealth of sound mathematical tools useful across disciplines; sets the stage for the emerging area of fast automatic differentiation; describes new designs for forecasting and control which exploit backpropagation; unifies concepts from Freud, Jung, biologists, and others into a new mathematical picture of the human mind and how it works; and certifies the viability of Deutsch's model of nationalism as a predictive tool - as well as the utility of extensions of this central paradigm.

Series Statement

Adaptive and learning systems for signal processing, communications, and control

Uniform Title

Adaptive and learning systems for signal processing, communications, and control

Subject

• Neural networks (Computer science)
• Regression analysis
• Prediction theory
• Neural Networks, Computer
• Regression Analysis
• Backpropagation-Algorithmus
• Neuronales Netz
• Prognose
• Regressionsanalyse
• Statistisches Modell
• Neurale netwerken
• Regressieanalyse
• Inteligencia artificial
• Analise de regressao e de correlacao

Note

• Published simultaneously in Canada.
• Originally presented as the author's thesis (Ph. D.--Harvard, 1974).
• "A Wiley-Interscience Publication."

Bibliography (note)

• Includes bibliographical references and index.

Contents

Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences -- 1. General Introduction and Summary -- 2. Dynamic Feedback, Statistical Estimation, and Systems Optimization: General Techniques -- 3. The Multivariate ARMA(1, 1) Model: Its Significance and Estimation -- 4. Simulation Studies of Techniques of Time-Series Analysis -- 5. General Applications of These Ideas: Practical Hazards and New Possibilities -- 6. Nationalism and Social Communications: A Test Case for Mathematical Approaches -- 7. Forms of Backpropagation for Sensitivity Analysis, Optimization, and Neural Networks -- 8. Backpropagation Through Time: What It Does and How to Do It -- 9. Neurocontrol: Where It Is Going and Why It Is Crucial -- 10. Neural Networks and the Human Mind: New Mathematics Fits Humanistic Insight.

ISBN

• 0471598976
• 9780471598978

LCCN

93023159

OCLC

• ocm28337564
• 28337564
• SCSB-2042816

Owning Institutions

Princeton University Library