Deep neural networks and their application for economic data processing
Thesis title in Czech: | Hluboké neuronové sítě a jejich využití při zpracování ekonomických dat |
---|---|
Thesis title in English: | Deep neural networks and their application for economic data processing |
Key words: | klasifikace, predikce, umělé neuronové sítě, konvoluční neuronové sítě, ekonomická data |
English key words: | classification, prediction, artificial neural networks, convolutional neural networks, economic data |
Academic year of topic announcement: | 2015/2016 |
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: | 07.12.2015 |
Date of assignment: | 08.12.2015 |
Confirmed by Study dept. on: | 15.12.2015 |
Date and time of defence: | 01.02.2017 10:30 |
Date of electronic submission: | 04.01.2017 |
Date of submission of printed version: | 04.01.2017 |
Date of proceeded defence: | 01.02.2017 |
Opponents: | Mgr. Tomáš Křen |
Guidelines |
The student shall review the following topics in his diploma thesis:
- overview and comparison of various paradigms applicable to classification / prediction of economic data by means of deep neural network architectures (multi-layered neural networks of the back-propagation type and convolutional neural networks) and their variants for temporal pattern processing (e.g., back-propagation through time, recurrent neural networks and recurrent convolutional neural networks) - recapitulation and mutual comparison of known techniques suitable for feature detection in economic data (e.g., correlation analysis, entropy-based models, sensitivity analysis, self-organizing feature maps, 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 financial data processing based on real-world data, e.g., from the World Bank, and will implement the models. The evaluation of the obtained results and gained experience shall form an important part of the thesis. |
References |
1. Některé z dostupných základních učebnic, resp. přehledových článků vhodných pro zvolené téma, např.:
- S. Haykin: Neural Networks and Learning Machines, 3rd edition, Pearson, (2009). - P. Berka: Dobývání znalostí z databází, Academia, (2003). - T. Kohonen: Self-Organizing Maps, Berlin: Springer, (2001). 2. Články: - E.J. Humphrey, J.P. Bello, Y. LeCun: Feature learning and deep architectures: new directions for music informatics, Journal of Intelligent Information Systems, 41(3), (2013), 461-481. - S. Lai, L. Xu, K. Liu, J. Zhao: Recurrent Convolutional Neural Networks for Text Classification, in: Proc. of the Twenty-Ninth AAAI Conference on Artificial Intelligence, AAAI, (2015), pp. 2267-2273. - 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. - P.O. Pinheiro, R. Collobert: Recurrent Convolutional Neural Networks for Scene Labeling, in: Proc. of the 31 st International Conference on Machine Learning (ICML), (2014), 9 p. - P. Sermanet, Y. LeCun: Traffic Sign Recognition with Multi-Scale Convolutional Networks, in: Proc. of IJCNN 2011, IEEE, (2011), pp. 2809-2813. 3. Aktuální články z profilujících světových časopisů, např.: Neurocomputing, Neural Networks, IEEE Transactions on Neural Networks ap. |