Simeon Simoff, 
"Connectionist Model For Handling Incomplete Knowledge - 
An Interval Approach", <i> Fuzzy Logic and the Management of 
Complexity (Proceedings of the 1996 International Discourse)</I>, 
UTS Publ., Sydney, Australia, 1996. 
<P><P>

	During the last decade there has been a considerable increase
	of activities in the field of connectionist modeling. Trying to
	override the limitations of the classical deterministic schema,
	various network models for dealing with uncertainty are
	continuously being developed. Most of them are based on
	stochastic and fuzzy data representations. On the other hand,
	in the sphere of reliable computations, data analysis and
	knowledge-based systems, there is an increasing popularity of
	interval analysis as a method for data processing and reasoning
	based on data with bounded errors.
<P>
	This paper aims on combining the interval representation of
	incomplete quantitative knowledge and connectionist models. The
	notion of an interval cell is defined as a building block of
	the model. The cell properties, including activation function,
	dynamic and learning properties, are examined. Attention is
	given to the problems connected with the explosion of interval
	uncertainty that results from repeated operations on interval
	values. Inference method is based on the propagation of the
	intervals across the network activating functions.

<P> S. Simoff