Abstract
In web age, the traditional information processing faces a new challenge. Due to the change of man-machine interaction modes, computers have to know the intention or interest of users. So computer information processing has to use the human brain processing principle for reference. One of its key principles is the multi-granular computing. In the talk, we will discuss the problem both from artificial intelligence and traditional information processing viewpoints. And we show that the new trend of information processing is to combine these two methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Serre, T., Oliva, A., Poggio, T.: A feed-forward architecture accounts for rapid categorization. Proc. of the National Academy of Sciences (PNAS) 104(15), 6424–6429 (2007)
Yao, J., Vasilakos, A.V., Pedryez, W.: Granular computing: perspectives and challenges. will appears in IEEE Trans. on Cybernetics (2012)
Zhang, B., Zhang, L.: Theory and Application of Problem Solving. North-Holland Elsevier Science Publishers B.V. (1992)
Hobbs, J.R.: Granularity. In: Proc. of IJCAI, Los, Angeles, USA, pp. 432–435 (1985)
Olshausen, B.: Emergence of simple-sell receptive properties by learning a sparse code for natural image. Nature (1996)
Benjio, Y., Lamblin, P., Popovici, D., Larochelle: Greedy layer-wise training of deep networks. In: Advances in Neural Information Processing Systems (NIPS 2006), vol. 19, pp. 153–160. MIT Press (2007)
Hinton, G.E., Osindero, S., Teh, Y.-W.: A fast learning algorithm for deep belief nets. Neural Communication 18, 1527–1554 (2006)
Le, Q.V., et al.: Building high level feature using large scale unsupervised learning. In: Proc. 29th ICML, Edinburgh, Scotland, UK (2012)
Hu, X., Qi, P., Zhang, B.: Hierarchical K-means algorithm for modeling visual area V2 neurons. In: 19th International Conference on Neural Information Processing, Doha, Qatar, November 12-15 (2012)
Baum, L.E., Petrie, T.: Statistical inference for probabilistic functions of finite state Markov chains. The Annals of Mathematical Statistics 37(6), 1554–1563 (1966)
Lafferty, J., et al.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proc. of International Conference on Machine Learning, ICML (2001)
Taskar, B., et al.: Max-margin Markov networks. In: Advances in Neural Information Processing Systems (INIPS) (2003)
Zhu, J., Xing, E., Zhang, B.: Laplace maximum margin Markov networks. In: Proc. of International Conference on Machine Learning (ICML) (2008)
Tenenbaum, J.E., et al.: How to grow a mind. Science 331(6022), 1279–1285 (2011)
Xu, M., Zhu, J., Zhang, B.: Bayesian non-parameter max-margin matrix factorization for collaborative prediction. In: Advances in Neural Information Processing Systems, NIPS (2012)
Zhu, J., Chen, N., Perkins, H., Zhang, B.: Gibbs max-margin supervised topic models with fast ampling algorithms. In: ICML (2013)
Xu, M., Zhu, J., Zhang, B.: Fast max-margin matrix factorization with data augmentation. In: ICML (2013)
Zhu, J., Zheng, X., Zhou, L., Zhang, B.: Scalable inference in max-margin topic models. In: SIGKDD (2013)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, B., Zhang, L. (2013). Multi-granular Computing in Web Age. In: Ciucci, D., Inuiguchi, M., Yao, Y., Ślęzak, D., Wang, G. (eds) Rough Sets, Fuzzy Sets, Data Mining, and Granular Computing. RSFDGrC 2013. Lecture Notes in Computer Science(), vol 8170. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41218-9_2
Download citation
DOI: https://doi.org/10.1007/978-3-642-41218-9_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41217-2
Online ISBN: 978-3-642-41218-9
eBook Packages: Computer ScienceComputer Science (R0)