Abstract
For the human-level intelligence simulation we should simulate it from the essence of intelligence and with the research results of brain science, cognitive science, artificial intelligence and others. In our study, a mental imagery knowledge representation mode had been established based on cognitive mechanism of human. Two kinds of table named mental imagery concept attributes table and concept attribute value ranges table had been used together to represent mental imagery knowledge in system. Mental imagery concept attributes table which formed by the thought of concept lattice was used to decide relations among concepts and attributes under the circumstance of coarse granularity. While concept attribute value ranges table was used to record differences of individual objects belong to the same concept under the circumstance of fine granularity. The concrete structured method of tables and decision-making process of system were described in the paper. Finally, the validity and feasibility of the knowledge representation mode are illustrated with real examples.
Keywords
- Human-level intelligence
- Knowledge representation mode
- Mental imagery
- Concept lattice
- Discernible attribute matrix
This research was supported by country science support plan, China (NO2007BAE7B01).
This is a preview of subscription content, access via your institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Shi, Z.-Z., Zheng, N.-N.: Progress and challenge of artificial intelligence. J.Comput. Sci & Technol. 21(5), 810–822 (2006)
Kosslyn, S.M.: The cognitive neuroscience of mental imagery. Neuropsychologia 33(11), 1335–1344 (1995)
Kosslyn, S.M., Shwartz, S.P.: A simulation of visual imagery. Cognitive Science 1, 265–295 (1977)
Ganis, G., Thompson, W.L., Kosslyn, S.M.: Brain areas underlying visual mental imagery and visual perception: an fMRI study. Cognitive Brain Research (20), 226–241 (2004)
Tye, M.: The Imagery Debate Cambridge, pp. 33–59. MIT Press, Cambridge (1991)
Barkowsky, T., Bertel, S., Engel, D., Freksa, C.: Design of an architecture for reasoning with mental images. In: International Workshop on Spatial and Visual Components in Mental Reasoning about Large-Scale Spaces, Bad Zwischenahn, Germany (September 01-02, 2003)
Hui, W., Xin-gui, H.: Knowledge Representation by Naive Mental Image. Chinese Journal of Computers 24(8), 891–896 (2001)
Hui, W., Yun-he, P.: The visual mental image base for thinking by image. Journal of Zhejiang University (Engineering Science) 35(2), 152–156 (2001)
Su, L., Xiang-lin, Q., Hong, H., Yun-jiu, W.: The phenomenon of functional column synchronous oscillatio. Science in China, Ser. C 34(4), 385–394 (2004)
Shou-jue, W., Yan-feng, Q., Wei-jun, L., Hong, Q.: Face Recognition: Biomimetic Pattern Recognition vs.Traditional Pattern Recognition. Acta Electronica Sinica 32(7), 1057–1061 (2004)
Chen, L.: The topological approach to perceptual organization. Visual Cognition 12(4), 553–701 (2005)
Qi, Z., Si-wei, L.: Sparse code neural network model based on visual system. Signal processing 19, 224–227 (2003)
Qi, Z., Si-wei, L., Yu, Z.: A computational model of object-based attention using multi-scale analysis and grouping. Acta Electronica Sinica 34(3), 559–562 (2006)
Zadeh, L.A.: Fuzzy sets and information granularity Advances in Fuzzy Set Theory and Application, pp. 3–18. North-Holland Publishing, Amsterdam (1979)
Ganter, B., Wille, R.: Formal Concept Analysis: Mathematical Foundations. Springer, Berlin (1999)
Wenxiu, Z., Guofang, Q.: Uncertain decision making based on rough sets, pp. 166–216. Tsinghua university Press (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ke, H., Zhang, D., You, W. (2009). Mental Imagery Knowledge Representation Mode of Human-Level Intelligence System. In: Wen, P., Li, Y., Polkowski, L., Yao, Y., Tsumoto, S., Wang, G. (eds) Rough Sets and Knowledge Technology. RSKT 2009. Lecture Notes in Computer Science(), vol 5589. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02962-2_29
Download citation
DOI: https://doi.org/10.1007/978-3-642-02962-2_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-02961-5
Online ISBN: 978-3-642-02962-2
eBook Packages: Computer ScienceComputer Science (R0)