Artificial neural networks and their application for 3D-data processing
Thesis title in Czech: | Umělé neuronové sítě a jejich využití při zpracování 3D-dat |
---|---|
Thesis title in English: | Artificial neural networks and their application for 3D-data processing |
Key words: | umělé neuronové sítě, N-dimenzionální konvoluční neuronové sítě, 3D data, klasifikace |
English key words: | artificial neural networks, N-dimensional convolutional neural networks, 3D data, classification |
Academic year of topic announcement: | 2011/2012 |
Thesis type: | diploma thesis |
Thesis language: | angličtina |
Department: | Department of Theoretical Computer Science and Mathematical Logic (32-KTIML) |
Supervisor: | doc. RNDr. Iveta Mrázová, CSc. |
Author: | hidden - assigned and confirmed by the Study Dept. |
Date of registration: | 12.01.2012 |
Date of assignment: | 12.01.2012 |
Confirmed by Study dept. on: | 27.02.2012 |
Date and time of defence: | 03.09.2012 11:30 |
Date of electronic submission: | 01.08.2012 |
Date of submission of printed version: | 02.08.2012 |
Date of proceeded defence: | 03.09.2012 |
Opponents: | RNDr. Tomáš Holan, Ph.D. |
Guidelines |
The student shall review the following topics in his diploma thesis:
- overview and comparison of various paradigms applicable to (pre)processing of 3D-data by means of self-organization (self-organizing feature maps and their variants with an adaptive topology - Growing Neural Gas Networks and Evolving Trees) - recapitulation and mutual comparison of known techniques suitable for feature detection and classification of 3D-data (e.g. multi-layered feed-forward neural networks of the back-propagation type, convolutional neural networks, Growing Hierarchical Neural Networks, etc.) - interpretation and visualization of the detected features and extracted knowledge The student will focus on some of these topics in more detail. Further, he will propose a suitable strategy for 3D-data processing based on real-world data and he shall implement the models. The evaluation of the obtained results and gained experience shall form an important part of the thesis. |
References |
Seznam doporučené literatury:
1. Některé z dostupných základních učebnic, resp. přehledových článků vhodných pro zvolené téma, např.: - S. Haykin: Neural networks: a comprehensive foundation, Prentice Hall, 1999 - T. Kohonen: Self-Organizing Maps, Berlin: Springer, 2001 - K.-L. Du: Clustering: A neural network approach, in: Neural Networks, Vol. 23 (2009) pp. 89-107. 2. Články: - Y. LeCun, L. Bottou, Y. Bengio, P. Haffner: Gradient-Based Learning Applied to Document Recognition, in: Proc. of the IEEE, vol. 86, no. 11 (Nov. 1998) pp. 2278-2324. - B. Fritzke: Growing Neural Gas Learns Topologies, in: Advances in Neural Information Processing Systems (1995), pp. 625-632. - E. Oja, J. Pakkanen, J. Iivarinen: The Evolving Tree - A Novel Self-Organizing Network for Data Analysis, in: Neural Processing Letters (2004), pp. 199-211. - I. Mrazova, M. Kukacka: Image Classification with GHNN-Networks, in: Proc. of the ICMV 2010 3rd Int. Conf. on Machine Vision, Hong Kong, IEEE New York (2010), pp. 223-227. - G. K. Knopf, A. Sangole, P. C. Igwe: Parametrization of Scattered Surface Points Using a SOFM, in: Intelligent Engineering Systems through Artificial Neural Networks, Vol. 13 (2003), pp. 33-38. 3. Aktuální články z profilujících světových časopisů, např.: Neurocomputing, Neural Networks, IEEE Transactions on Neural Networks ap. |