New Book: "Neural Networks"

[Raul Rojas]

This e-mail is to announce a new book on neural networks:

  "Neural Networks - A Systematic Introduction" by Raul Rojas,
  With a Foreword by Jerome Feldman,
  Springer-Verlag, Berlin-New York, 1996 (502 pp., 350 illustrations).

The book has a homepage with a sample chapter ("The Backpropagation
Algorithm", 33 pp.) that you are invited to download. The address
of the homepage is

  http://www.inf.fu-berlin.de/~rojas/neural

This is the Review which appeared in April in "Computing Reviews":

Connectionism and neural nets

Rojas, Raul (Univ. Halle, Halle, Germany)       9704-0262

Neural networks: a systematic introduction.
Springer-Verlag New York, Inc., New York, NY, 1996,
502 pp., $39.95, ISBN 3-540-60505-3.

If you want a systematic and thorough overview of neural networks, need a
good reference book on this subject, or are giving or taking a course on
neural networks, this book is for you. More generally, the book is of value
for anyone interested in understanding artificial neural networks or in
learning more about them. It attempts to solve the puzzle of artificial
neural models and proposals. Rojas systematically introduces and discusses
each of the neural network models in relation to the others.

The book is divided into 18 chapters, each designed to be taught in about
one week. The only mathematical tools needed to understand the text are
those learned during the first two years at university. The first eight
chapters form a logical sequence, and later ones can be covered in a
variety of orders. The first eight chapters are "The Biological Paradigm";
"Threshold Logic"; "Weighted Networks - The Perceptron"; "Perceptron
Learning"; "Unsupervised Learning and Clustering Algorithms"; "One and Two
Layered Networks"; "The Backpropagation Algorithm"; and "Fast Learning
Algorithms." The later chapters cover "Statistics and Neural Networks";
"The Complexity of Learning"; "Fuzzy Logic"; "Associative Networks"; "The
Hopfield Model"; "Stochastic Networks"; "Kohonen Networks"; "Modular Neural
Networks"; "Genetic Algorithms"; and "Hardware for Neural Networks." Proofs
are rigorous, but not overly formal, and the author makes extensive use of
geometric intuition and diagrams. There are a modest number of exercises at
the end of each chapter.

Material from the book has been used successfully for courses in Germany,
Austria and the United States. It seems quite extensive for a one-semester
course. Neural network applications are discussed, with the emphasis on
computational rather than engineering issues. Those who want to expend a
minimum amount of time and effort on a first overview of neural networks
and those who need to apply neural network technology in the most
cost-effective way for a specific task, should consult another reference as
well. On the whole, though, the author has done excellent work. The book
includes an index and an up-to-date and useful list of 473 references. The
German edition has been quite successful and has been through five
printings in three years. The English version has been radically rewritten
and deserves the same success.
                                            -J. Tepnadi, Tallinn, Estonia

---------------------