Predicate calculus feature generation

  • David Rothenberg
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 22)


A summary description (proof of theorems omitted): An adaptive pattern representation and recognition strategy for application to mechanized interpretation of (sampled) pictorial data (other applications are appropriate) is described. The system generates its own features which are formulae in a subset of the weak (in the sense that only quantification over finite sets is permitted) second order predicate calculus. The models of such formulae define the "objects" in a description of the data, which is hierarchical both with respect to features and extensions. The hierarchy is automatically constructed, thereby implementing changes in "problem representation". Relations between the syntax and semantics of formulae in the weak second order predicate calculus are derived (by extending the syntax of the calculus) and utilized. Minimal use is made of the finiteness of the input data by the methods employed. That is, in pictorial pattern recognitions, the adaptive feature generation (i.e., "learning") algorithms are independent of the fineness of grain of the sampling of an input picture. Because this approach is used, many difficult problems of a purely mathematical nature acquire practical importance. Computation is reduced through the use of topological methods and the system is at present in a stage of development appropriate for programming and use in a variety of practical applications.


Distributive Form Universal Quantifier Neutral Mutation Existential Quantifier Frechet Space 


  1. Addison, J., L. Henkin and A. Tarski (1965), "Theory of Models", Proc. 1963 International Symposium at Berkeley, North Holland Co., Amsterdam.Google Scholar
  2. Amarel, S. (1962), "An Approach to Automatic Theory Formation", in Principles of Self Organization, Trans. Illinois Symposium on Self Organization (Von Foerster and Zopf, Eds.), Pergamon Press, New York.Google Scholar
  3. Banerji, R. (1969), Theory of Problem Solving, An Approach to Artificial Intelligence, American Elsevier Publishing Co., Inc., New York.Google Scholar
  4. Bell, J. and A. Slomson (1969), Models and Ultraproducts, North Holland Co., Amsterdam.Google Scholar
  5. Block, H.D., N.J. Nilsson and R.O. Duda (1964), "Determination and Detection of Features in Patterns", Computer and Information Sciences (J. T. Tou and R. Wilcox, Eds), Spartan Books,. 75–110.Google Scholar
  6. Bongard, M. (1970), Pattern Recognition (J.H. Hawkins, Ed.), Spartan BooksGoogle Scholar
  7. Bremermann, H.J. (unpublished manuscript), "Artificial Intelligence and Neurobiology", Department of Mathematics, University of California, Berkeley.Google Scholar
  8. Ellentuck, E. (1971), "Direct Products of Relational Systems", U.S. Air Systems Command Final Report, Jan. 1, 1971 (see Rothenberg, 1971).Google Scholar
  9. Fogel, L.J., A.J. Owens, and M.J. Walsh (1966), Artificial Intelligence through Simulated Evolution, John Wiley and Sons, New York.Google Scholar
  10. Friedberg, R.M. (1958), "A Learning Machine, Part I", IBM J. Research and Development, 2, 2–13.Google Scholar
  11. Friedberg, R.M., B. Dunham and J.H. North (1959), "A Learning Machine, Part II", IBM J. Research and Development, 3, 282–287.Google Scholar
  12. Hawkins, J. (1970), "Textual Properties of Pattern Recognition", Picture Processes and and Psychopictorics (B.S. Lipkin and A. Rosenfeld, Eds), Academic Press, New York, 347–370.Google Scholar
  13. Hintikka, J. (1953), "Distributive Normal Forms in the Calculus of Predicates", Acta Philos. Fennica, 6, 1.Google Scholar
  14. Julesz, B. (1969), "Cluster Formation at Various Perceptual Levels", in Methodology of Pattern Recognition (S. Watanabe, Ed.), Academic Press, New York, 297–315.Google Scholar
  15. Kolers, P.A. (1970), "The Role of Shape and Geometry in Picture Recognition", Picture Processing and Psychopictorics (B.S. Lipkin and A. Rosenfeld, Eds.), Academic Press, New York, 181–202.Google Scholar
  16. Lee, R.C.R. (1967), "A Completeness Theorem and a Computer Program for Finding Theorems Derivable from Given Axioms", Ph.D. Dissertation, University of California at Berkeley.Google Scholar
  17. Lofgren, L. (1967), "Recognition of Order and Evolutionary Systems", in Computer and Information Science — II (J. Tou, Ed.), Academic Press, New York, 165–175.Google Scholar
  18. Minsky, M. (1963), "Steps Toward Artificial Intelligence", in Computers and Thought (E.A. Feigenbaum and J. Feldman, Eds.), McGraw-Hill Book Co., Inc., New York, 406–450.Google Scholar
  19. Muerle, J.L. (1970), "Some Thoughts on Texture Discrimination by Computer", Picture Processing and Psychopictorics (B.S. Lipkin and A. Rosenfeld, Eds.), Academic Press, New York, 371–380.Google Scholar
  20. Nilsson, N.J. (1971), Problem-solving Methods in Artificial Intelligence, McGraw-Hill Book Co., Inc., New York.Google Scholar
  21. Pessin, A. and D. Rothenberg (in preparation), The Weak Second Order Predicate Calculus as a Programming Language.Google Scholar
  22. Reyes, G.E. (1969), "Local Defineability Theory", Annals of Math. Logic, 1, 101.Google Scholar
  23. Rosenfeld, A. and B. Lipkin (1970), "Texture Analysis", in Picture Processing and Psychopictorics (B. Lipkin and A. Rosenfeld, Eds.), Academic Press, New York, 309–347.Google Scholar
  24. Rothenberg, D. (1971), "An Adaptive Linguistic Model for Pattern Representation and Recognition", Final Report, Air Force Systems Command, USAF, Directorate of Mathematical and Informational Sciences, January 1, 1971.Google Scholar
  25. Rothenberg, D. (1973a), "A Pattern Recognition Model Applied to the Perception of Pitch", AFOSR Technical Report, January 1969, revised version to appear as series of articles in Mathematical Systems Theory. See also this volume.Google Scholar
  26. Rothenberg, D. (1973b), "A Theory of Feature Generation", a series of four articles to be submitted to Mathematical Systems Theory (Copies available from Mathematics Department, Rutgers University, University College, New Brunswick, New Jersey).Google Scholar
  27. Schoenfeld, J. (1967), Mathematical Logic, Addison Wesley, Reading, Massachusetts.Google Scholar
  28. Selfridge, O.G. and U. Neisser (1963), "Pattern Recognition by Machine", in Computers and Thought (E.A. Feigenbaum and J. Feldman, Eds.), McGraw-Hill Book Co., Inc., New York, 237–250.Google Scholar
  29. Sherman, R. and G.W. Ernst (1969), "Learning Patterns in Terms of Other Patterns", in Pattern Recognition, Pergamon Press, New York, (Vol. 1), 301–313.Google Scholar
  30. Sierpinsky, (1952), General Topology, University of Toronto Press, Toronto.Google Scholar
  31. Slagle, J., C. Chang and R. Lee (1969), "Completeness Theorems for Semantic Resolution in Consequence Finding", Proc. International Joint Conference on Artificial Intelligence, May 7–9, 1969, Washington, D.C. (D.E. Walker and J.M. Norton, Eds.), 281–285.Google Scholar
  32. Solomonoff, R.J. (1964), "A Formal Theory of Inductive Inference — Part I", Information and Control, 7, 1–22.Google Scholar
  33. Solomonoff, R.J. (1964), "A Formal Theory of Inductive Inference — Part II", Information and Control, 7, 224–254.Google Scholar
  34. Uhr, L. and C. Vossler (1963), "A Pattern Recognition Program that Generates, Evaluates, and Adjusts its Own Operators", in Computers and Thought, (E.A. Feigenbaum and J. Feldman, Eds.), McGraw-Hill Book Co., Inc., New York, 251–268.Google Scholar
  35. Wang, H. (1960), "Toward Mechanical Mathematics", IBM J. Research and Development, 4, 2–22.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1975

Authors and Affiliations

  • David Rothenberg
    • 1
  1. 1.University College, Rutgers UniversityUSA

Personalised recommendations