Hostname: page-component-586b7cd67f-r5fsc Total loading time: 0 Render date: 2024-11-24T03:52:03.090Z Has data issue: false hasContentIssue false
  • English
  • Français

AN ALTERNATIVE METHOD OF CONCEPT LEARNING

Part of: Artificial intelligence (68Txx)

Published online by Cambridge University Press:  06 March 2017

SEN WANG Open the ORCID record for SEN WANG [Opens in a new window] ,
QINGXIANG FANG Open the ORCID record for QINGXIANG FANG [Opens in a new window]  and
JUN-E FENG Open the ORCID record for JUN-E FENG [Opens in a new window]
SEN WANG
Affiliation:
School of Mathematics, Shandong University, Jinan 250100, China email [email protected], [email protected]
QINGXIANG FANG
Affiliation:
School of Science, China Jiliang University, Hangzhou 310018, China email [email protected]
JUN-E FENG*
Affiliation:
School of Mathematics, Shandong University, Jinan 250100, China email [email protected], [email protected]
*
✉[email protected]
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

We solve the problem of concept learning using a semi-tensor product method. All possible hypotheses are expressed under the framework of a semi-tensor product. An algorithm is raised to derive the version space. In some cases, the new approach improves the efficiency compared to the previous approach.

Keywords

concept learningversion spacesemi-tensor producttarget conceptall possible hypotheses

MSC classification

Primary: 68T01: General
Type
Research Article
Information
The ANZIAM Journal , Volume 58 , Issue 3-4 , April 2017 , pp. 211 - 219
Copyright
© 2017 Australian Mathematical Society 

References

Cheng, D., “Semi-tensor product of matrices and its application to Morgen’s problem”, Sci. China Inf. Sci. 44 (2001) 195–212; doi:10.1007/BF02714570.Google Scholar
Cheng, D. and Qi, H., “Controllability and observability of Boolean control networks”, Automatica 45 (2009) 1659–1667; doi:10.1016/j.automatica.2009.03.006.Google Scholar
Cheng, D. and Qi, H., “A linear representation of dynamics of Boolean networks”, IEEE Trans. Automat. Control 55(10) (2010) 2251–2258; doi:10.1109/TAC.2010.2043294.Google Scholar
Cheng, D., Qi, H., Li, Z. and Liu, J., “Stability and stabilization of Boolean networks”, Internat. J. Robust Nonlinear Control 21 (2011) 134–156; doi:10.1002/rnc.1581.CrossRefGoogle Scholar
Haussler, D., “Quantifying inductive bias: AI learning algorithms and Valiant’s learning framework”, Artificial Intelligence 36 (1988) 177–221; doi:10.1016/0004-3702(88)90002-1.Google Scholar
Mitchell, T. M., Machine learning (McGraw-Hill, Boston, MA, 1997); https://www.iitgn.ac.in/sites/default/files/library_files/2016/19032016.pdf.Google Scholar
Mitchell, T. M., “Version spaces: a candidate elimination approach to rule learning”, in: IJCAI’77 Proceedings of the 5th international joint conference on Artificial intelligence - Volume 1 (Morgan Kaufmann Publishers Inc., San Francisco, CA, 1977) 305–310; http://dl.acm.org/citation.cfm?id=1624501.Google Scholar
Zhao, Y., Qi, H. and Cheng, D., “Input-state incidence matrix of Boolean control networks and its applications”, Systems Control Lett. 59 (2010) 767–774; doi:10.1016/j.sysconle.2010.09.002.Google Scholar