Deep Neural Networks for Time Series Forecasting
Thesis title in Czech: | Předpovídání časových řad pomocí hlubokých neuronových sítí |
---|---|
Thesis title in English: | Deep Neural Networks for Time Series Forecasting |
Key words: | hluboké učení, časové řady, předpovídání |
English key words: | deep learning, time series, forecasting |
Academic year of topic announcement: | 2017/2018 |
Thesis type: | diploma thesis |
Thesis language: | angličtina |
Department: | Department of Theoretical Computer Science and Mathematical Logic (32-KTIML) |
Supervisor: | Mgr. Martin Pilát, Ph.D. |
Author: | hidden - assigned and confirmed by the Study Dept. |
Date of registration: | 10.01.2018 |
Date of assignment: | 12.02.2018 |
Confirmed by Study dept. on: | 25.04.2019 |
Date and time of defence: | 03.02.2020 09:00 |
Date of electronic submission: | 06.01.2020 |
Date of submission of printed version: | 06.01.2020 |
Date of proceeded defence: | 03.02.2020 |
Opponents: | Mgr. Roman Neruda, CSc. |
Guidelines |
Deep neural networks have gained a lot of attention in the recent years and they are considered state of the art in the areas of image classification, natural language translation etc. However, their applications to time-series forecasting are as of yet rather uncommon. The goal of this thesis is to investigate such applications of deep learning.
The student will study the available literature on deep neural networks and time-series forecasting and based on the acquired knowledge will design and implement new models of neural networks for time series forecasting. The newly implemented methods will be compared to existing methods on publicly available time series, e.g. exchange rates and stock quotes. |
References |
[1] Jianbo Yang, Minh Nhut Nguyen, Phyo Phyo San, Xiaoli Li, and Shonali Krishnaswamy. "Deep Convolutional Neural Networks on Multichannel Time Series for Human Activity Recognition." In Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI 2015), pp. 3995-4001. AAAI Press 2015. ISBN: 978-1-57735-738-4.
[2] Enzo Busseti, Ian Osband, and Scott Wong. "Deep learning for time series modeling." Technical report, Stanford University (2012). [3] Ian Goodfellow, Yoshua Bengio, Aaron Courville: "Deep Learning". MIT Press 2016. ISBN: 978-0-26203-561-3 |