Aplikace hlubokých neuronových sítí v multimediálních databázích
Thesis title in Czech: | Aplikace hlubokých neuronových sítí v multimediálních databázích |
---|---|
Thesis title in English: | Applications of deep neural networks in multimedia databases |
Key words: | Hluboké neuronové sítě, hluboké učení, multimediální databáze |
English key words: | Deep neural networks, deep learning, multimedia databases |
Academic year of topic announcement: | 2015/2016 |
Thesis type: | dissertation |
Thesis language: | |
Department: | Department of Software Engineering (32-KSI) |
Supervisor: | doc. RNDr. Jakub Lokoč, Ph.D. |
Author: | hidden - assigned and confirmed by the Study Dept. |
Date of registration: | 03.10.2016 |
Date of assignment: | 03.10.2016 |
Confirmed by Study dept. on: | 03.10.2016 |
Guidelines |
With the huge expansion of multimedia databases and variability of the data, both novel feature extraction and similarity search models are required for effective retrieval. Recently, deep learning approaches have reached state-of-the-art results in many benchmarks and shifted the research in this field towards biologically inspired approaches. The goal of this work is to analyze and design novel deep learning architectures, as well as to apply features from deep neural networks in specific multimedia applications. |
References |
A. Krizhevsky, I. Sutskever, and G. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, 2012.
C. Szegedy, Wei Liu, Yangqing Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke and A. Rabinovich. Going deeper with convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Guillaume Alain and Yoshua Bengio. What regularized auto-encoders learn from the data-generating distribution. Journal of Machine Learning Research 15(1): 3563-3593 (2014). Yoshua Bengio, Aaron C. Courville, and Pascal Vincent. Representation Learning: A Review and New Perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8): 1798-1828 (2013). |