Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Classical methods for interpreting objective function minimization as intelligent inference

Conference ·
OSTI ID:466459
 [1]
  1. Univ. of Texas, Dallas, TX (United States)

Most recognition algorithms and neural networks can be formally viewed as seeking a minimum value of an appropriate objective function during either classification or learning phases. The goal of this paper is to argue that in order to show a recognition algorithm is making intelligent inferences, it is not sufficient to show that the recognition algorithm is computing (or trying to compute) the global minimum of some objective function. One must explicitly define a {open_quotes}relational system{close_quotes} for the recognition algorithm or neural network which identifies the: (i) sample space, (ii) the relevant sigmafield of events generated by the sample space, and (iii) the {open_quotes}relation{close_quotes} for that relational system. Only when such a {open_quotes}relational system{close_quotes} is properly defined, is it possible to formally establish the sense in which computing the global minimum of an objective function is an intelligent, inference.

OSTI ID:
466459
Report Number(s):
CONF-9610138--
Country of Publication:
United States
Language:
English

Similar Records

What is computational intelligence?
Conference · Fri Dec 30 23:00:00 EST 1994 · OSTI ID:81587

Multidimensional neural growing networks and computer intelligence
Journal Article · Tue Feb 28 23:00:00 EST 1995 · Cybernetics and Systems Analysis · OSTI ID:457589

Intelligent robots and computer vision IX: Algorithms and techniques; Proceedings of the Meeting, Boston, MA, Nov. 5-7, 1990
Conference · Mon Dec 31 23:00:00 EST 1990 · OSTI ID:7273595