Using FCA for Encoding Closure Operators into Neural Networks
DOI: 10.1007/978-3-540-73681-3_24
关键词:
摘要: After decades of concurrent development symbolic and connectionist methods, recent years have shown intensifying efforts integrating those two paradigms. This paper contributes to the methods for transferring present knowledge into representations. Motivated by basic ideas from formal concept analysis, we propose ways directly encoding closure operators on finite sets in a 3-layered feed forward neural network.
springer.com
sci-hub.st 参考文章(8)
L. Lamb, H. Barringer, J. Woods, A. Garcez, S. Artemov, We Will Show Them: Essays in Honour of Dov Gabbay ,(2005)
Bernhard Ganter, Rudolf Wille, C. Franzke, Formal Concept Analysis: Mathematical Foundations ,(1998)
Artur S. d'Avila Garcez, Dov M. Gabbay, Krysia B. Broda, Neural-Symbolic Learning Systems: Foundations and Applications ,(2012)
Sebastian Bader, Pascal Hitzler, Dimensions of Neural-symbolic Integration — A Structured Survey We Will Show Them! (1). pp. 167- 194 ,(2005)
Warren S. McCulloch, Walter Pitts, A logical calculus of the ideas immanent in nervous activity Bulletin of Mathematical Biology. ,vol. 52, pp. 99- 115 ,(1990) , 10.1007/BF02478259
William F. Dowling, Jean H. Gallier, Linear-time algorithms for testing the satisfiability of propositional horn formulae Journal of Logic Programming. ,vol. 1, pp. 267- 284 ,(1984) , 10.1016/0743-1066(84)90014-1
Pascal Hitzler, Steffen Hölldobler, Anthony Karel Seda, Logic programs and connectionist networks Journal of Applied Logic. ,vol. 2, pp. 245- 272 ,(2004) , 10.1016/J.JAL.2004.03.002
David Maier, The theory of relational databases ,(1983)