# SMART GROWING CELLS

### Hendrik Annuth, Christian-A. Bohn

#### Abstract

General unsupervised learning or self-organization places n-dimensional reference vectors in order to match the distribution of samples in an n-dimensional vector space. Beside this abstract view on self-organization there are many applications where training — focused on the sample distribution only — does not lead to a satisfactory match between reference cells and samples. Kohonen’s self-organizing map, for example, overcomes pure unsupervised learning by augmenting an additional 2D topology. And although pure unsupervised learning is restricted therewith, the result is valuable in applications where an additional 2D structure hidden in the sample distribution should be recognized. In this work, we generalize this idea of application-focused trimming of ideal, unsupervised learning and reinforce it through the application of surface reconstruction from 3D point samples. Our approach is based on Fritzke’s growing cells structures (GCS) (Fritzke, 1993) which we extend to the smart growing cells (SGC) by grafting cells by a higher-level intelligence beyond the classical distribution matching capabilities. Surface reconstruction with smart growing cells outperforms most neural network based approaches and it achieves several advantages compared to classical reconstruction methods.

#### References

- Boissonnat, J.-D. (1984). Geometric structures for threedimensional shape representation. ACM Trans. Graph., 3(4):266-286.
- Edelsbrunner, H. and Mcke, E. P. (1994). dimensional alpha shapes.
- Fritzke, B. (1993). Growing cell structures - a selforganizing network for unsupervised and supervised learning. Neural Networks, 7:1441-1460.
- Fritzke, B. (1995). A growing neural gas network learns topologies. In Tesauro, G., Touretzky, D. S., and Leen, T. K., editors, Advances in Neural Information Processing Systems 7, pages 625-632. MIT Press, Cambridge MA.
- Hoffmann, M. and Vrady, L. (1998). Free-form surfaces for scattered data by neural networks. Journal for Geometry and Graphics, 2:1-6.
- Hoppe, H. (2008). Poisson surface reconstruction and its applications. In SPM 7808: Proceedings of the 2008 ACM symposium on Solid and physical modeling, pages 10-10, New York, NY, USA. ACM.
- Hoppe, H., DeRose, T., Duchamp, T., McDonald, J. A., and Stuetzle, W. (1992). Surface reconstruction from unorganized points. In Thomas, J. J., editor, SIGGRAPH, pages 71-78. ACM.
- Huang, Q.-X., Adams, B., and Wand, M. (2007). Bayesian surface reconstruction via iterative scan alignment to an optimized prototype. In SGP 7807: Proceedings of the fifth Eurographics symposium on Geometry processing, pages 213-223, Aire-la-Ville, Switzerland, Switzerland. Eurographics Association.
- Ivrissimtzis, I., Jeong, W.-K., Lee, S., Lee, Y., and Seidel, H.-P. (2004a). Neural meshes: surface reconstruction with a learning algorithm. Research Report MPII-2004-4-005, Max-Planck-Institut für Informatik, Stuhlsatzenhausweg 85, 66123 Saarbr ücken, Germany.
- Ivrissimtzis, I., Jeong, W.-K., and Seidel, H.-P. (2003a). Neural meshes: Statistical learning methods in surface reconstruction. Technical Report MPI-I-2003-4-007, Max-Planck-Institut fr Informatik, Saarbrücken.
- Ivrissimtzis, I., Lee, Y., Lee, S., Jeong, W.-K., and Seidel, H.-P. (2004b). Neural mesh ensembles. In 3DPVT 7804: Proceedings of the 3D Data Processing, Visualization, and Transmission, 2nd International Symposium, pages 308-315, Washington, DC, USA. IEEE Computer Society.
- Ivrissimtzis, I. P., Jeong, W.-K., and Seidel, H.-P. (2003b). Using growing cell structures for surface reconstruction. In SMI 7803: Proceedings of the Shape Modeling International 2003, page 78, Washington, DC, USA. IEEE Computer Society.
- Kohonen, T. (1982). Self-organized formation of topologically correct feature maps. Biological cybernetics, 43:59-69.
- Kolluri, R., Shewchuk, J. R., and O'Brien, J. F. (2004). Spectral surface reconstruction from noisy point clouds. In SGP 7804: Proceedings of the 2004 Eurographics/ACM SIGGRAPH symposium on Geometry processing, pages 11-21, New York, NY, USA. ACM.
- MacQueen, J. B. (1967). Some methods for classification and analysis of multivariate observations. In Proceedings of 5th Berkeley Symposium on Mathematical Statistics and Probability, pages 281 - 297. University of California Press.
- Storvik, G. (1996). Bayesian surface reconstruction from noisy images. In In Interface 96.
- Taubin, G. (1995). A signal processing approach to fair surface design. In SIGGRAPH, pages 351-358.
- Vrady, L., Hoffmann, M., and Kovcs, E. (1999). Improved free-form modelling of scattered data by dynamic neural networks. Journal for Geometry and Graphics, 3:177-183.
- Yoon, M., Lee, Y., Lee, S., Ivrissimtzis, I., and Seidel, H.- P. (2007). Surface and normal ensembles for surface reconstruction. Comput. Aided Des., 39(5):408-420.
- Yu, Y. (1999). Surface reconstruction from unorganized points using self-organizing neural networks. In In IEEE Visualization 99, Conference Proceedings, pages 61-64.

#### Paper Citation

#### in Harvard Style

Annuth H. and Bohn C. (2010). **SMART GROWING CELLS** . In *Proceedings of the International Conference on Fuzzy Computation and 2nd International Conference on Neural Computation - Volume 1: ICNC, (IJCCI 2010)* ISBN 978-989-8425-32-4, pages 227-237. DOI: 10.5220/0003085202270237

#### in Bibtex Style

@conference{icnc10,

author={Hendrik Annuth and Christian-A. Bohn},

title={SMART GROWING CELLS},

booktitle={Proceedings of the International Conference on Fuzzy Computation and 2nd International Conference on Neural Computation - Volume 1: ICNC, (IJCCI 2010)},

year={2010},

pages={227-237},

publisher={SciTePress},

organization={INSTICC},

doi={10.5220/0003085202270237},

isbn={978-989-8425-32-4},

}

#### in EndNote Style

TY - CONF

JO - Proceedings of the International Conference on Fuzzy Computation and 2nd International Conference on Neural Computation - Volume 1: ICNC, (IJCCI 2010)

TI - SMART GROWING CELLS

SN - 978-989-8425-32-4

AU - Annuth H.

AU - Bohn C.

PY - 2010

SP - 227

EP - 237

DO - 10.5220/0003085202270237