2.9 Further Reading
There exist many fundamental books on neural networks that cover most neural network structures of interest. Some examples are the following:
S. Haykin (1999), Neural Networks: A Comprehensive Foundation, Second Edition, Macmillan, New York.
J. Herz, A. Krough, R.G. Palmer (1991), Introduction to the Theory of Neural Computation, AddisonWesley, Reading, MA.
M.H. Hassoun (1995), Fundamentals of Artificial Neural Networks, The MIT Press, Cambridge, MA.
The following book concerns neural network simulation in Mathematica. It does not give very much background information on neural networks and their algorithms, but contains programs and simulation examples. The book is not based on the Neural Network package. Instead, the book contains the code for some neural network models.
J. A. Freeman (1994), Simulating Neural Networks with Mathematica, AddisonWesley, Reading, MA.
System identification and timeseries prediction are broad and diverse fields, and there exist many general and specialized books on these topics. The following list contains just some samples of the vast literature.
The following are good introductory books:
L. Ljung and T. Glad (1994), Modeling of Dynamic Systems, Prentice Hall, Englewood Cliffs, NJ.
R. Johansson (1993), System Modeling and Identification, Prentice Hall, Englewood Cliffs, NJ.
The following books are more thorough and they are used in graduate courses at several universities:
L. Ljung (1999), System Identification: Theory for the User, Second Edition, Prentice Hall, Englewood Cliffs, NJ.
T. Söderström and P. Stoica (1989), System Identification, Prentice Hall, Englewood Cliffs, NJ.
The following article discusses possibilities and problems using nonlinear identification methods from a user's perspective:
J. Sjöberg et al. (1995), NonLinear BlackBox Modeling in System Identification: A Unified Overview, Automatica, vol. 31. no. 12, pp. 16911724.
This book is a standard reference for timeseries problems:
G.E.P. Box and G.M. Jenkins (1976), Time Series Analysis, Forecasting and Control, HoldenDay, Oakland, CA.
Many modern approaches to timeseries prediction can be found in this book and in the references therein:
A.S. Weigend and N.A. Gershenfeld (Editors) (1994), Time Series Prediction: Forecasting the Future and Understanding the Past, AddisonWesley, Proceedings of the NATO Advanced Research Workshop on Comparative Time Series Analysis Held in Santa Fe, New Mexico, May 1417, 1992.
In most cases the neural network training is nothing other than minimization and it is, therefore, a good idea to consult standard books on minimization, such as:
J.E. Dennis and R.B. Schnabel (1983), Numerical Methods for Unconstrained Optimization and Nonlinear Equations, Prentice Hall, Englewood Cliffs, NJ.
R. Fletcher (1987), Practical Methods of Optimization, John Wiley & Sons, Chippenham, Great Britain.
