Artificial neural networks (ANNs) are relatively new computational tools th
at have found extensive utilization in solving many complex real-world prob
lems. The attractiveness df ANNs comes from their remarkable information pr
ocessing characteristics pertinent mainly to nonlinearity, high parallelism
, fault and noise tolerance, and learning and generalization capabilities.
This paper aims to familiarize the reader with ANN-based computing (neuroco
mputing) and to serve as a useful companion practical guide and toolkit for
the ANNs modeler along the course of ANN project development. The history
of the evolution of neurocomputing and its relation to the field of neurobi
ology is briefly discussed. ANNs are compared to both expert systems and st
atistical regression and their advantages and limitations are outlined. A b
ird's eye review of the various types of ANNs and the related learning rule
s is:presented, with special emphasis on backpropagation (BP) ANNs theory a
nd design. A generalized methodology for developing successful ANNs project
s from conceptualization to design, to implementation, is described. The mo
st common problems that BPANNs developers face during training are summariz
ed in conjunction with possible causes and remedies. Finally, as a practica
l application, BPANNs were used to model the-microbial growth curves of S.
flexneri. The developed model was reasonably accurate in simulating both tr
aining: and test time-dependent growth curves as affected by temperature an
d pH. (C) 2000 published by Elsevier Science B.V.