Thesis supervisor: Bálint Gyires-Tóth
Location of studies (in Hungarian): Távközlési és Médiainformatikai Tanszék Abbreviation of location of studies: TMIT
Description of the research topic:
Deep learning has revolutionized many research areas, like speech recognition and synthesis, image classification and segmentation, and natural language understanding. The modeling performance of deep learning systems significantly surpass earlier machine learning methods due to their ability to extract and to learn various abstractions of huge amount of input data. However, in case of few training data their performance remains typically poor and unbalanced data leads to the same phenomena. Generally deep neural networks have ‘black-box’ type behavior – the reasoning and inference rule of deep learning systems stays unknown throughout the whole process.
In contrast humans are capable of learning complex processes based on only few samples by transferring the knowledge of similar domains. Humans can also explain the logic behind their reasoning and inference.
The goal of the current research is to create novel algorithms that helps to understand and extract the reasoning of deep neural networks and to be able to transfer and share the learned knowledge among deep learning systems from similar domains. Thus few learning examples will be enough for training new neural networks. The effectiveness of the elaborated method must be proven at least in one application scenario. Such an application scenario can be (1) audio/image segmentation and classification, (2) language modeling, (3) speech synthesis, etc.
The research can be performed 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 PhD student are the following:
- Overview the related scientific papers, including basic deep neural networks elements and novel results in knowledge extraction from neural networks and transfer learning.
- Design and implement a baseline system for modeling training samples of similar domains separately.
- Elaborate novel algorithms to extract the knowledge from trained neural networks and transfer it to a new network from similar domain.
- Demonstrate the effectiveness of the results at least in one application scenario.
- Objective and subjective evaluation.
Required language skills: english Further requirements: Basic programming and mathematical skills
Number of students who can be accepted: 1
Deadline for application: 2017-01-03
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).
Login
