stu4@larry.mcrcim.mcgill.edu (Craig Jones) (01/23/91)
Please forgive the next question (it has probably been asked many times before.) I am wondering if anyone could suggest some introductory level books in the area of Neural Networks. Preferably something within a student's budget. Please reply by e-mail and if others are interested I will post a summary later. Thanks. Craig Jones bnrmtl!stu4@larry.mcrcim.mcgill.edu
bakker@batserver.cs.uq.oz.au (Paultje Bakker) (01/24/91)
In article <1991Jan22.173911.779@scrumpy@.bnr.ca> bnrmtl!stu4@larry.mcrcim.mcgill.edu writes: >I am wondering if anyone could suggest some introductory >level books in the area of Neural Networks. Preferably >something within a student's budget. > (Yes, Virginia, this request has come up before. I might turn this into a regular 3-monthly posting... please mail any new additions to bakker@batserver.cs.uq.oz.au. Comments on the books would also be very useful.) SUMMARY OF RESPONSES to the request for: "A good, general, *readable* introduction to neural networks" October 1990. ******************************************* Rumelhart D.E and McClelland J.L Parallel Distributed Processing Vols 1 & 2 MIT, Cambridge 1986 It's quite readable, and affordable (about $65 for both volumes). A companion volume 'Explorations in PDP' by McClelland is written in a tutorial style, and includes 2 diskettes of NN simulation programs that can be compiled on MS-DOS or Unix (and they do too !) A paper by Rumelhart et.al published in Nature at the same time (vol 323 October 1986) gives a very good potted explanation of backprop NN's. It gives sufficient detail to write your own NN simulation. ----------------------------------- I Aleksander, H Morton: An Introduction to Neural Computing Chapman and Hall, 1990. ----------------------------------- Books: >From CS point of view: %A P. D. Wasserman %T Neural Computing: Theory and Practice %I Van Nostrand Reinhold %C New York %D 1989 >From AI point of view: %A M. Zeidenberg %C Chichester %D 1990 %I Ellis Horwood, Ltd. %T Neural Networks in Artificial Intelligence >From Psych point of view (note the bulk): %A D. E. Rumelhart %A J. L. McClelland %D 1986 %I The MIT Press %K PDP-1 %T Parallel Distributed Processing: Explorations in the Microstructure of Cognition %o (volume 1) %A J. L. McClelland %A D. E. Rumelhart %D 1986 %I The MIT Press %K PDP-2 %T Parallel Distributed Processing: Explorations in the Microstructure of Cognition %o (volume 2) %A J. L. McClelland %A D. E. Rumelhart %D 1988 %I The MIT Press %T Explorations in Parallel Distributed Processing: Computational Models of Cognition and Perception Papers: %A R. P. Lippmann %D April 1987 %J IEEE Transactions on Acoustics, Speech, and Signal Processing %V 2 %N 4 %P 4--22 %T An introduction to computing with neural nets %X Much acclaimed as an overview of neural networks, but rather inaccurate on several points. The categorization into binary and continuous-valued input neural networks is rather arbitrary, and may work confusing for the unexperienced reader. Not all networks discussed are of equal importance. %A G. E. Hinton %T Connectionist learning procedures %J Artificial Intelligence %V 40 %D 1989 %P 185--234 %X One of the better neural networks overview papers, although the distinction between network topology and learning algorithm is not always very clear. Could very well be used as an introduction to neural networks. ------------------------ D. Wunsch (ed.) (1991) Neural Networks : An Introduction. ------------------------ "Naturally Intelligent Systems" by Caudill, Maureen and Charles Butler. Cambridge, Massachusetts: MIT Press, (1990). ISBN 0-262-03156-6 (about 300 pages) ------------------------- Yoh-Han Pao, Adaptive Pattern Recognition and Neural Nets, c. 1989 by Addison-Wesley Publishing Company, Inc. ------------------------ Neural Computing an Introduction by R. Beale and T. Jackson. It's $30.00 and published by Adam Hilger (ISBN 0-85274-262-2). It's clearly written. Lots of hints as to how to get the adaptive models covered to work (not always well explained in the original sources). Consistent mathematical terminology. Covers perceptrons, error-backpropagation, Kohonen self-org model, Hopfield type models, ART, and associative memories. ************************************ Wasserman seemed to be the most popular choice. Thanks to James Tizard, Patrick van der Smagt, Guszti Bartfai, Don Wunsch, Andy, Lilly Spirkovska and Nathan Brown. Paul Bakker bakker@batserver.cs.uq.oz.au -- --Paul Bakker email: bakker@batserver.cs.uq.oz.au --Dept. of Scatology "Love between the ugly --University of Qld Is the most beautiful love of all" --Gondwanaland - T. Rundgren
smagt@fwi.uva.nl (Patrick van der Smagt) (01/24/91)
In article <6929@uqcspe.cs.uq.oz.au> bakker@batserver.cs.uq.oz.au writes: >In article <1991Jan22.173911.779@scrumpy@.bnr.ca> bnrmtl!stu4@larry.mcrcim.mcgill.edu writes: >>I am wondering if anyone could suggest some introductory >>level books in the area of Neural Networks. Preferably >>something within a student's budget. >Thanks to James Tizard, Patrick van der Smagt, Guszti Bartfai, Don Wunsch, >Andy, Lilly Spirkovska and Nathan Brown. > Here're some more: No formulas at all( ==> no good): %A M. McCord Nelson %A W. T. Illingworth %T A Practical Guide to Neural Nets %I Addison-Wesley %D 1990 Not so bad (with a page of erroneous formulas (if I remember well), and #hidden layers isn't well described): %A Tharun Khanna %T Foundations of Neural Networks %I Addison-Wesley %D 1990 Patrick K. Simpson, "Artificial Neural Systems", Pergamon Press, 1990 Finally: Hecht-Nielsen (Addison-Wesley, 1990) nice but rather randomly pasted together. Good in some aspects, less good in others. Why did he include topic such-and-such and not topic so-and-so? Yet quite thorough at times. Patrick van der Smagt -- P.S. New address from Feb. 1: University of Amsterdam Dept. of Computer Systems Kruislaan 403
schraudo@beowulf.ucsd.edu (Nici Schraudolph) (01/29/91)
Don't forget "Introduction to the Theory of Neural Computation" by Hertz,
Krogh & Palmer (Addison-Wesley 1991). Though I haven't read my copy yet
(it only just came out), my first impression is that this one is by far the
best book on the topic. At NIPS, where it was first introduced, the general
reaction was "looks like there's finally a good textbook on neural nets".
And it's below $30 for the paperback.
>Wasserman seemed to be the most popular choice.
This statement made me cringe - am I the only one who considers Wasserman
a, pardon me, next to useless book? I could go on and on about the reasons
for my dislike, but IMHO this book is not even worth wasting bandwidth for
that. Suffice it to say that Wasserman flatly enumerates some common
architectures from an engineer's perspective ("how it works") without ever
addressing the underlying fundamentals ("why it works") - important basic
concepts such as clustering, principal components or gradient descent are
not treated. It's also full of errors, and unhelpful diagrams drawn with
what appears to be PCB board layout software from the '70s.
Wasserman may be acceptable for the applied engineer who quickly wants to
try a neural net at his problem, and feels he doesn't need to *understand*
the algorithms he is using. This approach is of course easier on the reader,
which may partly explain the apparent popularity of this book. For anyone
who wants to do active research in the field I consider it quite inadequate.
Disclaimer: sprinkle the above with IMHOs as needed.
PS: I will send my copy of Wasserman to the first victim, er, person who
is willing to pay for the postage. No-income people have priority.
--
Nicol N. Schraudolph, C-014 | "And long cars in long lines
University of California, San Diego | And great big signs, and they all say:
La Jolla, CA 92093-0114 | Hallelujah. Every man for himself."
nici%cs@ucsd.{edu,bitnet,uucp} | - Laurie Anderson, "Big Science".usenet@winnie.fit.edu (USENET News System) (01/30/91)
1991, ISBN 0-201-50395-6 [hbk], ISBN0-201-51560-1 [pbk]). It provides a good balance of model development, computational algorithms, and applications. The mathematical derivations are especially well done. Another interesting new book is "A Practical Guide to Neural Nets", by Nelson and Illingworth (Addison-Wesley, 1991, ISBN 0-201-52376-0). It does not have much detailed model development (very few equations), but it does present many areas of application. It includes a chapter on current areas of research. Some people who have recently inquired about existing commercial applications of neural networks could find a variety of such in chapter 1. It also includes a program diskette with a fancy graphical interface (unlike the PDP diskette).