On data classification by iterative linear partitioning

Discrete Applied Mathematics

Volumn 144, Issue 1-2, 2004, Pages 2-16

  Anthony, Martin ^a  

^a LONDON SCHOOL OF ECONOMICS   (United Kingdom)

Author keywords

Decision lists; Hyperplanes; Multi class classification; Pattern classification

Indexed keywords

ALGORITHMS; COMPUTATIONAL COMPLEXITY; DATA MINING; ERROR ANALYSIS; FUNCTION EVALUATION; ITERATIVE METHODS; LEARNING SYSTEMS; MATHEMATICAL MODELS; PATTERN RECOGNITION; SET THEORY;

DECISION LISTS; GOODNESS-OF-FIT; HYPERPLANES; MULTI-CLASS CLASSIFICATION;

LINEAR PROGRAMMING;

EID: 4544370785     PISSN: 0166218X     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.dam.2004.04.003     Document Type: Article

References (45)

1. M. Anthony, Threshold functions, decision lists, and the representation of Boolean functions, Neurocolt Technical Report NC-TR-96-028, 1996.
2. M. Anthony, Discrete Mathematics of Neural Networks: Selected Topics, SIAM Monographs on Discrete Mathematics and Applications, Society for Industrial and Applied Mathematics, Philadelphia, PA, 2001.
3. M. Anthony, Generalization error bounds for threshold decision lists, J. Mach. Learn. Res. 5 (2004) 189-217.
4. M. Anthony, Partitioning points by parallel planes, RUTCOR Research Report RRR-39-2002, Rutgers Center for Operations Research (Also, CDAM research report LSE-CDAM-2002-10, Centre for Discrete and Applicable Mathematics, London School of Economics), Discrete Math., 282 (2004) 17-21.
5. M. Anthony, P.L. Bartlett, Neural Network Learning: Theoretical Foundations, Cambridge University Press, Cambridge, 1999.
6. M. Anthony, N.L. Biggs, Computational Learning Theory: An Introduction, Cambridge Tracts in Theoretical Computer Science, Vol. 30, Cambridge University Press, Cambridge, UK, 1992.
7. M. Anthony, G. Brightwell, J. Shawe-Taylor, On specifying Boolean functions by labelled examples, Discrete Appl. Math. 61 (1995) 1-25.
8. M. Anthony, J. Shawe-Taylor, Using the perceptron algorithm to find consistent hypotheses, Combinatorics Probab. Comput. 4 (2) (1993) 385-387.
9. E. Baum, D. Haussler, What size net gives valid generalization?, Neural Comput. 1 (1) (1989) 151-160.
10. J.C. Bioch, Dualization decision lists and identification of monotone discrete functions, Ann. Math. Artificial Intell. 24 (1998) 69-91.
11. A. Blum, R.L. Rivest, Training a 3-node neural network is NP-complete, Neural Networks 5 (1) (1992) 117-127.
12. A. Blumer, A. Ehrenfeucht, D. Haussler, M.K. Warmuth, Learnability and the Vapnik-Chervonenkis dimension, J. ACM 36 (4) (1989) 929-965.
13. V. Bohossian, J. Bruck, Multiple threshold neural logic, M. Jordan, M. Kearns, S. Solla(Eds.), Advances in Neural Information Processing, Vol. 10, NIPS' 1997, MIT Press, Cambridge, 1998.
14. T.M. Cover, Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition, IEEE Trans. Electron. Comput. 14 (1965) 326-334.
15. L. Devroye, L. Györfi, G. Lugosi, A Probabilistic Theory of Pattern Recognition, Springer, Berlin, 1996.
16. A. Ehrenfeucht, D. Haussler, M. Kearns, L. Valiant, A general lower bound on the number of examples needed for learning, Inform. Comput. 82 (1989) 247-261.
17. P.L. Hammer, T. Ibaraki, U.N. Peled, Threshold numbers and threshold completions, Ann. Discrete Math. 11 (1981) 125-145.
18. R.G. Jeroslow, On defining sets of vertices of the hypercube by linear inequalities, Discrete Math. 11 (1975) 119-124.
19. N. Karmarkar, A new polynomial time algorithm for linear programming, Combinatorica 4 (1984) 373-395.
20. M. Krause, On the computational power of Boolean decision lists, in: Proceedings of the 19th Annual Symposium of Theoretical Aspects of Computer Science (STACS), 2002.
21. N. Linial, Y. Mansour, R.L. Rivest, Results on learnability and the Vapnik-Chervonenkis dimension, Inform. Comput. 90 (1) (1991) 33-49.
22. N. Littlestone, Learning quickly when irrelevant attributes abound: a new linear threshold learning algorithm, Mach. Learn. 2 (4) (1988) 245-318.
23. O.L. Mangasarian, Multisurface method of pattern separation, IEEE Trans. Inform. Theory IT-14 (6) (1968) 801-807.
24. M. Marchand, M. Golea, On learning simple neural concepts: from halfspace intersections to neural decision lists, Network: Comput. Neural Systems 4 (1993) 67-85.
25. M. Marchand, M. Golea, P. Ruján, A convergence theorem for sequential learning in two-layer perceptrons, Europhys. Lett. 11 (1990) 487.
26. M. Minsky, S. Papert, Perceptrons, MIT Press, Cambridge, MA, 1969 (Expanded edition 1988).
27. B.K. Natarajan, On learning sets and functions, Mach. Learn. 4 (1) (1989) 67-97.
28. A. Ngom, A. Obradović, I. Stojmenović, Minimization of multiple-valued multiple-threshold perceptrons using genetic algorithms, in: Proceedings of the 28th IEEE International Symposium on Multiple-Valued Logic, IEEE Press, New York, 1998.
29. A. Ngom, C. Reischer, D. Simovici, I. Stojmenović, Learning with permutably homogeneous multiple-valued multiple-threshold perceptrons, in: Proceedings of the 28th IEEE International Symposium on Multiple-Valued Logic, IEEE Press, New York, 1998.
30. A. Ngom, I. Stojmenović, J. Žunić, On the number of multilinear partitions and the computing capacity of multiple- valued multiple-threshold perceptrons, in: Proceedings of 29th IEEE International Symposium on Multiple-Valued Logic, IEEE Press, New York, 1999.
31. N.J. Nilsson, Learning Machines, McGraw-Hill, New York, 1965.
32. A.B. Novikoff, On convergence proofs on perceptrons, Symposium on the Mathematical Theory of Automata, Vol. 12, Polytechnic Institute of Brooklyn 1962, pp. 615-622.
33. Z. Obradović, I. Parberry, Learning with discrete multivalued neurons, J. Comput. System Sci. 49 (1994) 375-390.
34. S. Olafsson, Y.S. Abu-Mostafa, The capacity of multilevel threshold functions, IEEE Trans. Pattern Anal. Mach. Intell. 10 (2) (1988) 277-281.
35. L. Pitt, L. Valiant, Computational limitations on learning from examples, J. ACM 35 (1988) 965-984.
36. R. Rivest, Learning decision lists, Mach. Learn. 2 (3) (1987) 229-246.
37. F. Rosenblatt, The perceptron: a probabilistic model for information storage and organization in the brain, Psychol. Rev. 65 (1958) 386-407.
38. J. Shawe-Taylor, P. Bartlett, R.C. Williamson, M. Anthony, Structural risk minimisation over data-dependent hierarchies, IEEE Trans. Inform. Theory 44 (5) (1998) 1926-1940.
39. R. Takiyama, The separating capacity of a multi-threshold element, IEEE Trans. Pattern Anal. Mach. Intell. 7 (1985) 112-116.
40. G. Turán, F. Vatan, Linear decision lists and partitioning algorithms for the construction of neural networks, in: Foundations of Computational Mathematics selected papers of a conference Springer, Rio de Janeiro, 1997, pp. 414-423.
41. V.N. Vapnik, Estimation of Dependences Based on Empirical Data, Springer, New York, 1982.
42. V.N. Vapnik, Statistical Learning Theory, Wiley, New York, 1998.
43. V.N. Vapnik, A.Y. Chervonenkis, On the uniform convergence of relative frequencies of events to their probabilities, Theory Probab. Appl. 16 (2) (1971) 264-280.
44. A. Zuev, L.I. Lipkin, Estimating the efficiency of threshold representations of Boolean functions, Cybernetics 24 (1988) 713-723(translated from Kibernetika (Kiev) 6 (1988) 29-37).
45. A. Zuev, L.I. Lipkin, Estimating the efficiency of threshold representations of Boolean functions, Cybernetics 24 (1988) 713-723(translated from Kibernetika (Kiev) 6 (1988) 29-37).