Autoencoder based generators of semi-artificial data

Jaka Klančar (2018) Autoencoder based generators of semi-artificial data. MSc thesis.

Preview

Abstract

The goal of the thesis is to alleviate the problem of insufficient data available for data analysis or machine learning. We developed a generator of semi-artificial data based on autoencoders. We implemented dynamic autoencoders without any predefined structure, as we wanted that our solution is general and may therefore be used on any data set. Results showed that autoencoder based generators work better than variational autoencoders. The generators perform best on data sets with a small number of mixed attributes and balanced classes. They perform better if more training instances are available. Results additionally show that grid search significantly improves the performance and that it is possible to predict a good set of parameters for each data set.

Item Type:

Thesis (MSc thesis)

Keywords:

autoencoders, data generators, neural networks, semi-artifical data, variational autoencoders

Number of Pages:

Language of Content:

English

Mentor / Comentors:

Name and Surname	ID	Function
prof. dr. Marko Robnik Šikonja	276	Mentor

Link to COBISS:

http://www.cobiss.si/scripts/cobiss?command=search&base=51012&select=(ID=1537833155)

Institution:

University of Ljubljana

Department:

Faculty of Computer and Information Science

Item ID:

4141

Date Deposited:

22 Jun 2018 15:29

Last Modified:

06 Jul 2018 13:51

URI:

http://eprints.fri.uni-lj.si/id/eprint/4141

Actions (login required)

View Item