Gyires-Tóth Bálint
Knowledge Representation and Reasoning in Deep Learning


Intézmény: Budapesti Műszaki és Gazdaságtudományi Egyetem
informatikai tudományok
Informatikai Tudományok Doktori Iskola

témavezető: Gyires-Tóth Bálint
helyszín (magyar oldal): Távközlési és Médiainformatikai Tanszék
helyszín rövidítés: TMIT

A kutatási téma leírása:

Detailed description of 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 surpasses 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 examples, their performance remains typically poor and new data leads to catastrophic forgetting of previous knowledge. 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 help to understand and extract the reasoning and consider knowledge representation in deep neural networks. Thus, fewer learning examples will be enough to train neural networks and the training process may be aided by previous knowledge. 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, memory-augmented neural networks, one-shot learning and Bayesian Deep 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.

előírt nyelvtudás: english
további elvárások: 
Basic programming and mathematical skills

felvehető hallgatók száma: 1

Jelentkezési határidő: 2018-07-31

Minden jog fenntartva © 2007, Országos Doktori Tanács - a doktori adatbázis nyilvántartási száma az adatvédelmi biztosnál: 02003/0001. Program verzió: 2.2358 ( 2017. X. 31. )