Newsgroups: comp.ai,comp.ai.neural-nets,sci.engr.control
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!pipex!sunsite.doc.ic.ac.uk!yama.mcc.ac.uk!cf-cm!thor.cf.ac.uk!spexl
From: spexl@thor.cf.ac.uk (Mr X Liu 92)
Subject: New book information
Message-ID: <21987.9505250919@thor.cf.ac.uk>
Sender: spexl@thor.cf.ac.uk (Mr X Liu 92)
Organization: University of Wales College of Cardiff, Cardiff, Wales, UK
Date: Thu, 25 May 1995 10:19:12 +0100
X-Mailer: Cardiff Computing Maths PP Mail Open News Gateway
Lines: 62
Xref: glinda.oz.cs.cmu.edu comp.ai:30119 comp.ai.neural-nets:24308 sci.engr.control:5691

** NEW BOOK ** NEW BOOK ** NEW BOOK ** NEW BOOK **


Neural       Networks      for     Identification,
Prediction and Control

by D T Pham and X Liu
Intelligent Systems Laboratory
University of Wales Cardiff, UK.

Springer-Verlag  (London, Berlin, Heidelberg,  New
York)

ISBN 3-540-19959-4   238 pp

Price (May 1995): UK Pounds 35; US$ 69; DM 88


This   book   describes examples  of  applications
of  neural   networks  in   modelling,  prediction
and   control.    The   topics   covered   include
identification of   general   linear    and   non-
linear    processes, forecasting  of river levels,
stock    market   prices  and   currency  exchange
rates, and control of a timedelayed    plant   and
a  two-joint   robot.   These applications  employ
the    major   types   of    neural  networks  and
learning  algorithms.  The  neural  network  types
considered    in   detail   are   the   multilayer
perceptron  (MLP), the Elman and  Jordan  networks
and   the   Group-Method-of-Data-Handling   (GMDH)
network.   In   addition,   cerebellar-     model-
articulation-controller   (CMAC)   networks    and
neuromorphic   fuzzy  logic  systems   are    also
presented.  The main  learning  algorithm  adopted
in     the    applications   is   the     standard
backpropagation     (BP)    algorithm.     Widrow-
Hoff   learning,   dynamic  BP  and   evolutionary
learning  are also described.

The  book  is  aimed  at  electrical,  electronic,
control   and    systems    engineers    concerned
with     system  identification,  prediction   and
control  who   wish  to explore   neural   network
approaches.   For  readers unfamiliar with  neural
computing,   the   book    provides   a    concise
introduction to the main existing types of  neural
networks.  The book also gives full   listings  of
computer  programs written in C for neural-network
based    system   identification  and   prediction
to   facilitate    experimentation   with   neural
network techniques.


For     sales    information,   please     contact
Sales   Department,    Springer-Verlag,    London,
Sweetapple   House,  Catteshall  Road,  Godalming,
Surrey  GU7 3DJ UK telephone  +44  (0)1483  418822
fax       +44      (0)1483     415151,      e-mail
postmaster@svl.co.uk


