Abstract
The ways to transform a wide class of machine learning algorithms into processes of plausible reasoning based on known deductive and inductive rules of inference are shown. The employed approach to machine learning problems is based on the concept of a good classification (diagnostic) test for a given set of positive and negative examples. The problem of inferring all good diagnostic tests is to search for the best approximations of the given classification (partition or the partitioning) on the established set of examples. The theory of algebraic lattice is used as a mathematical language to construct algorithms of inferring good classification tests. The advantage of the algebraic lattice is that it is given both as a declarative structure, i.e., the structure for knowledge representation, and as a system of dual operations used to generate elements of this structure. In this work, algorithms of inferring good tests are decomposed into subproblems and operations that are the main rules of plausible human inductive and deductive reasoning. The process of plausible reasoning is considered as a sequence of three mental acts: implementing the rule of reasoning (inductive or deductive)with obtaining a new assertion, refining the boundaries of reasoning domain, and choosing a new rule of reasoning (deductive or inductive one).
Similar content being viewed by others
References
S. Muggleton and L. De Raert, “Inductive Logic Programming: Theory and Methods,” Journal of Logic Programming 19/20, 629–679 (1994).
N. Lavrac, D. Gamberger, and V. Jovanoski, “A Study of Relevance for Learning in Deductive Databases,” Journal of Logic Programming 40((2/3)), 215–249 (1999).
N. Lavrac and P. Flash, An Extended Transformation Approach to Inductive Logic Programming, CSTR-00-002 (University of Bristol, Department of Computer Science, Bristol, 2000).
F. Lisi and D. Malerba, “Inducing Multi-Level Association Rules from Multiple Relations,” Machine Leaning 55, 175–210 (2004).
M. Schmidt-Schauss and G. Smolka, “Attributive Concept Descriptions with Complements,” Artif. Intell. 48(1), 1–26 (1991).
C. Ceri, G. Gotlob, and L. Tanca Logic Programming and Databases (Springer, 1990).
C. Giraud-Carrier and T. Martinez, “An Incremental Learning Model for Commonsense Reasoning,” in Proceedings of 7th International Symposium on Artificial Intelligence, ISAI’94, 1994, pp. 134–141.
V. K. Finn, “Inductive Models of Knowledge Representation in Man-Machine and Robotic Systems,” in Proceedings of VINITI A, 58–76 (1984).
V. K. Finn, “Plausible Conclusions and Plausible Reasoning,” Itogi Nauki i Tekhniki, Ser. Probability Theory, Mathematical Statistics, and Technical Cybernetics 28, 3–84 (1988).
V. K. Finn, “Plausible Reasoning in Intelligent Systems of JSM type,” Itogi Nauki I Tekhniki, Ser. Informatika 15, 54–101 (1991).
V. K. Finn, “Synthesis of Cognitive Procedures and Induction Problem,” NTI, Ser. 2., Nos. 1, 2, 8–44 (1999).
M. I. Zabezhailo, V. G. Ivashko, S. O. Kuznetsov, et al., “Algorithmic and Programming JSM ToolsAlgorit-micheskie i programmnye sredstva JSM, a Method of Automatic Hypotheses Generation,” NTI, Ser. 2., No. 10, 1–14 (1987).
D. S. Mill, A System of Syllogistical and Inductive Logic (Knizhnoe delo, Moscow, 1900) [in Russian].
C. S. Peirce, Philosophical Writings of Peirce, Ed. by L. Buchler (Dover Publications, N.Y., 1995), pp. 150–156.
D. V. Vinogradov, “Logical Programs for Quasi-Axiomatic Theories,” NTI, Ser. 2., Nos. 1, 2, 61–64 (1999).
B. A. Galitsky, S. O. Kuznetsov, and D. V. Vinogradov, JASMINE: A Hybrid Reasoning Tool for Discovering Causal Links in Biological Data, http://www.dcs. bbk.ac.uk/~galitsky/Jasmine.
O. M. Anshakov, D. P. Skvortsov, and V. K. Finn, “Logical Tools of the JSM-Method of Automatic Generation of Hypotheses: A System of Rules and Its Deductive Simulation,” NTI, Ser. 2., No. 11, 21–30 (1987).
K. A. Naidenova and Yu. G. Polezhaeva, “An Algorithm for Constructing Good Diagnostic Tests,” in Proceedings of 4th All-Union Conference on Application of Methods of Mathematical Logic, Tallinn, Estoniya, 1986, pp. 63–67.
K. A. Naidenova, “Reduction of Machine Learning Problems to Approximation of a Given Classification on the Set of Examples,” in Proceedings of 5th National Conference with International Participation on Artificial Intelligence (Tatarstan, Kazan, 1996), Vol. 1, pp. 275–279 [in Russian].
J. Ganascia, “Gabriel. EKAW-89 Tutorial Notes: Machine Learning,” in Proceedings of 3rd European Workshop on Knowledge Acquisition for Knowledge-Based Systems, Paris, France, 1989, pp. 287–296.
C. Carpineto and G. Romano, “A Lattice Conceptual Clustering System and Its Application to Browsing Retrieval,” Machine Learning, No. 24, 95–122 (1996).
J. Demetrovics and D. T. Vu, “Generating Armstrong Relation Schemes and Inferring Functional Dependencies from Relations,” Int. J. Information Theory & Applications 1(4), 3–12 (1993).
H. Mannila and K. J. Raiha, “On the Complexity of Inferring Functional Dependencies,” Discrete Applied Mathematics 40, 237–243 (1992).
H. Mannila and K. Raiha, “J. Algorithm for Inferring Functional Dependencies,” in Data & Knowledge Engineering 12, 83–99 (1994).
Y. Huntala, J. Karkkainen, P. Porkka, et al., “TANE: An Efficient Algorithm for Discovering Functional and Approximate Dependencies,” The Computer J. 42, 100–111 (1999).
S. Cosmadakis, P. Kanellakis, and N. Spyratos, “Partition Semantics for Relations,” J. Computer and System Sciences 33(2), 203–233 (1986).
I. A. Megretskaya, “Construction of Natural Classifying Tests in Generation of Knowledge Bases,” in Problems of Application of Expert Systems in National Economy (Moldaviya, Chisinau, 1988), pp. 89–93 [in Russian].
K. A. Naidenova, “Machine Learning as a Diagnostic Task,” in Proceedings of the Short-Term Scientific Workshop on Knowledge-Dialogue-Solution Ad. by I. Arefiev, St-Petersburg, Russia, 26–36 (1992).
K. A. Naidenova, Yu. G. Polezhaeva, and Yu. G. Iserlis, “The Concept of Knowledge Eliciting Based on the Best Diagnostic Tests,” in Proceedings of International Conference on Knowledge-Dialogue-Solution,” Yalta, Ukraine, 1995, Vol. 1, pp. 85–95.
K. A. Naidenova, M. V. Plaksin, and V. L. Shagalov, “Inductive Inferring All Good Classification Tests,” in Proceedings of International Conference on Knowledge-Dialog-Solution, Yalta, Ukraine, 1995, Vol. 1, pp. 79–84.
K. A. Naidenova, “DIAGARA: An Incremental Algorithm for Inferring Implicative Rules from Examples,” Int. J. Information Theories and Applications 12(2), 171–186 (2005).
K. A. Naidenova, “An Incremental Learning Algorithm for Inferring Implicative Rules from Examples,” in Data Mining and Knowledge Discovery Approaches Based on Rule Induction Techniques, Ed. by G. Triantaphillou and G. Felici (Springer, New York, 2006), pp. 89–147.
G. Stumme, R. Taouil, Y. Bastide, et al., “Fast Computation of Concept Lattices Using Data Mining Techniques,” in Proceedings of 7th International Workshop on Knowledge Representation Meets Databases, KRDB’2000, pp. 129–139.
N. E. Mephu and P. Njiwoua, “Using Lattice Based Framework as a Tool for Feature Extraction,” in Feature Extraction, Construction, and Selection: A Data Mining Perspective, Ed. by H. Lui and H. Motoda (Kluwer, 1998).
R. Wille, “Concept Lattices and Conceptual Knowledge System,” Computer Math. Appl. 23(6–9), 493–515 (1992).
G. Stumme, R. Taouil, Y. Bastide, et al., “Fast Computation of Concept Lattices Using Data Mining Techniques,” in Proceedings of 7th International Workshop on Knowledge Representation Meets databases, KRDB’2000, pp. 129–139.
C. E. Dowling, “On the Irredundant Generation of Knowledge Spaces,” J. Math. Psych. 37(1), 49–62 (1993).
S. Salzberg, “A Nearest Hyper Rectangle Learning Method,” Machine Learning 6, 277–309 (1991).
B. Ganter, Two Basic Algorithms in Concepts Analysis, FB4-Preprint No. 831, TH Darmstadt, 1984.
L. Nourine and O. Raynaud, “A Fast Algorithm for Building Lattices,” Information Processing Letters 71, 199–204 (1999).
S. O. Kuznetsov, “A Fast Algorithm for Constructing All Intersections of Objects from a Finite Semi-Lattice,” NTI, Ser. 2., No. 1, 17–20 (1993).
S. O. Kuznetsov and S. A. Obiedkov, “Comparing Performance of Algorithms for Generating Concept Lattices,” J. Exp. Theor. Artif. Intell. 14(2, 3), 183–216 (2001).
O. Ore, “Galois Connections,” Trans. Amer. Math. Society 55(1), 493–513 (1944).
J. Riguet, “Relations Binaires, Fermetures, Correspondences De Galois,” Bull. Soc. Math. 76(3), 114–155 (1948).
R. Wille, “Restructuring Lattice Theory: An Approach Based on Hierarchies of Concept,” in Ordered Sets (Reidel, Dordrecht-Boston, 1982), pp. 445–470.
J.-G. Ganascia, “CHARADE: A Rule Learning System,” in Proceedings of 10 th International Joint Conference on Artificial Intelligence (IJCAI), Milan, Italy, 1987, pp. 345–347.
E. Sperner, “Eine Satz Uber Untermengen Einer Endlichen Menge,” Mat. Z. 27(11), 544–548 (1928).
D. Polya, Mathematics and Plausible Reasoning (IL, Moscow, 1957) [in Russian].
R. S. Michalski, “A Theory and Methodology of Inductive Learning,” Artif. Intell. 20, 111–161 (1983).
K. A. Naidenova and J. G. Polegaeva, “SISIF, the System of Knowledge Acquisition from Experimental Facts,” in Proceedings of 3 rd International Conference on Industrial Applications of Artificial Intelligence, Ed. by L. James and L. I. Mikulich (North-Holland, Amsterdam, 1991), pp. 87–92.
R. Agraval and R. Srikant, “Fast Algorithms for Mining Association Rules,” in Proceedings of 20 th VLDB Conference, Santiago, Chile, pp. 487–499.
R. S. Michalski and I. B. Larsen, “Selection of Most Representative Training Examples and Incremental Generation of VL1 Hypotheses: The Underlying Methodology and the Description of Programs ESEL and AQII,” Report No. 78-867, University of Illinois at Urbana-Campaign, IL, USA, 1978.
K. A. Naidenova and A. E. Ermakov, “Decomposition of the Inference Algorithm for Good Diagnostic Tests,” in Proceedings of 4 th International Conference on Computer-Aided design of Discrete Devices, CAD D D’2001, Minsk, Belarus, 2001, Vol. 3, pp. 61–69.
H. Rasiova, An Algebraic Approach to Non-Classical Logic (North-Holland, Amsterdam-London, 1974).
Author information
Authors and Affiliations
Additional information
Original Russian Text © K.A. Naidenova, 2009, published in Izvestiya Akademii Nauk. Teoriya i Sistemy Upravleniya, 2009, No. 3, pp. 73–88.
Rights and permissions
About this article
Cite this article
Naidenova, K.A. Reducing one class of machine learning algorithms to logical operations of plausible reasoning. J. Comput. Syst. Sci. Int. 48, 401–414 (2009). https://doi.org/10.1134/S1064230709030083
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1064230709030083