Thesis (Selection of subject)Thesis (Selection of subject)(version: 336)
Assignment details
   Login via CAS
Artificial neural networks for pattern recognition
Thesis title in Czech: Rozpoznávání vzorů pomocí neuronových sítí
Thesis title in English: Artificial neural networks for pattern recognition
Academic year of topic announcement: 2006/2007
Type of assignment: diploma thesis
Thesis language: angličtina
Department: Department of Software Engineering (32-KSI)
Supervisor: doc. RNDr. Iveta Mrázová, CSc.
Author: hidden - assigned and confirmed by the Study Dept.
Date of registration: 09.10.2006
Date of assignment: 09.10.2006
Date and time of defence: 28.01.2008 00:00
Date of electronic submission:28.01.2008
Date of proceeded defence: 28.01.2008
Reviewers: RNDr. Petr Božovský, CSc.
The student shall discuss the following areas in his diploma thesis:

- recapitulation and comparison of various different paradigms applicable
to pattern recognition (and character recognition, resp.) - these will include
especially models based on back-propagation, Kohonen self-organizing
feature maps, genetic algorithms and decision trees
- pre-processing of the input data and feature selection
- adaptive and automatic detection of significant input parameters.

Some of the above-stated areas should be discussed in more detail. Based on the chosen real-world data
(probably from the area of character recognition), the student shall propose a suitable strategy for the whole process of pattern recognition. Further, he shall implement some of the respective models and evaluate the obtained results.
1. Some of the textbooks suitable for the chosen area, e.g.:
- C. M. Bishop: Neural Networks for Pattern Recognition, Oxford University Press,
- R. Rojas: Neural Networks: A Systematic Introduction, Springer-Verlag, 1996
- S. Haykin: Neural Networks: A Comprehensive Foundation, Prentice Hall, Upper
Saddle River, N. J., 1999
- V. N. Vapnik: The Nature of Statistical Learning Theory, 2nd edition,
Springer-Verlag, 2000

2. Current articles from relevant journals - Neurocomputing, Neural Networks, etc.
Charles University | Information system of Charles University |