A Hybrid Intelligent Architecture and Its
		 Application to Water Reservoir Control

                Ismail Taha and Joydeep Ghosh

Measured inputs  in  control  domains  are  often  continuous.  A
discretization  function  is needed to map continuous inputs into
multiple intervals or ranges of input values, so that they can be
used  as  symbolic inputs to a rule-based system. The discretiza-
tion parameters used to determine each interval play  a  critical
role  in  the  overall effectiveness of a rule-based system. This
paper introduces a Hybrid Intelligent Architecture (HIA) that ex-
ploits  the  complementary features of expert systems and connec-
tionist architectures to revise the initial domain knowledge  and
enhance  its  input  characterization.  HIA  has  three  building
blocks: a Knowledge-Based module, a Statistical module and a Con-
nectionist  Architecture module. A well defined format is used to
describe the initial  knowledge  acquired  from  the  application
domain  in  a  rule-based format and to enable its mapping into a
uniform, three layer network. The statistical module updates both
the rule-based and the connectionist subsystems by observing cer-
tain correlations among input-input and input-output  pairs.  The
backpropagation algorithm is augmented to allow refining of input
discretization functions and extracting new domain  knowledge.  A
successful  application  of  the proposed concepts to control the
water reservoirs of Colorado river  near  Austin,  is  described.
Moreover,  the  public  domain  breast cancer data set is used to
show the importance of the statistical module in extracting rules
when no prior domain knowledge is available.