Due to the revolutionary increase in the amount of available data, the rise of high-performance GPUs and the novel results in neural networks, deep learning has received high attention among machine learning techniques. The numerous layers of deep architectures are able to extract different abstractions of the input data (based on observations of real life) and predict or classify them efficiently.
State-of-the-art image/video and time series segmentation, classification and recognition solutions are generally based on deep learning methodology. Novel elements, like various types of deep convolutional and recurrent neural networks, are able to learn the descriptive features of the signals' content in many representation levels. This approach is proven to overcome the previously used feature extraction methods and can even surpass the accuracy of human annotators.
Audio, visual information and temporal data are often completed or accompanied by textual information. The textual information may be presented in various formats including precise labels, textual description or even free text. Deep learning based algorithms are capable of extracting information from such sources. Combining the features extracted from the original signals with the semantics of the textual information may increase the modeling capacity of the overall model.
The goal of this Ph.D. research is to elaborate novel deep learning methods to jointly analyze and model heterogeneous data. The effectiveness of the elaborated method must be proven at least in one application scenario. Such an application scenario can be(1) speech technologies, (2) natural language processing, (3) images and meta-data from other data sources, etc.
The research can be conducted both in English and in Hungarian. For training the models public and private databases and high-performance GPUs are available.
The possible research tasks of the Ph.D. student are the following:
• Overview the related scientific papers, including the basic deep neural network elements and novel results in deep learning based classification.
• Design and implement baseline systems for separate analysis of audio/visual/textual data from heterogeneous sources with basic deep learning algorithms and enhance it with novel deep learning methods,.
• Conduct research on the joint analysis of heterogeneous data with deep learning. Propose a novel method with improved modeling capacity.
• Demonstrate the effectiveness of the results at least in one application scenario.
• Objective and subjective evaluation.
előírt nyelvtudás: english felvehető hallgatók száma: 1
Jelentkezési határidő: 2019-01-07
2024. IV. 17. ODT ülés Az ODT következő ülésére 2024. június 14-én, pénteken 10.00 órakor kerül sor a Semmelweis Egyetem Szenátusi termében (Bp. Üllői út 26. I. emelet).
Bejelentkezés
