Mateusz Dorobek

Mateusz Dorobek
Warsaw University of Technology · Faculty of Mathematics and Information Science

Master of Science

About

4
Publications
1,403
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
9
Citations
Citations since 2017
4 Research Items
9 Citations
201720182019202020212022202301234567
201720182019202020212022202301234567
201720182019202020212022202301234567
201720182019202020212022202301234567
Introduction
I’m a master’s student in Data Science at Warsaw University of Technology in Poland. My main area of the current research is in the Music Generation and analysis using Deep Learning techniques.

Publications

Publications (4)
Article
Full-text available
Forecasting is one of the cognitive methods based on empirical knowledge supported by appropriate modeling methods that give information about the way the relations between factors and how the phenomenon under study will develop in the future. In this article, a selection is made of a suitable architecture for a predictive model for a set of data o...
Preprint
This thesis is presenting a method for generating short musical phrases using a deep convolutional generative adversarial network (DCGAN). To train neural network were used datasets of classical and jazz music MIDI recordings. Our approach introduces translating the MIDI data into graphical images in a piano roll format suitable for the network inp...
Chapter
Full-text available
In this paper we have presented a method for composing and generating short musical phrases using a deep convolutional generative adversarial network (DCGAN). We have used a dataset of classical and jazz music MIDI recordings in order to train the network. Our approach introduces translating the MIDI data into graphical images in a piano roll forma...
Thesis
Full-text available
This thesis is presenting a method for generating short musical phrases using a deep convolutional generative adversarial network (DCGAN). To train neural network were used datasets of classical and jazz music MIDI recordings. Our approach introduces translating the MIDI data into graphical images in a piano roll format suitable for the network inp...

Network

Cited By

Projects

Project (1)
Project
The goal of this project is to create a system capable to predict the next chord based on earlier ones. I plan to test embedding for chords based on expert knowledge and automatic techniques. The main area of this work is jazz due to its high variance and completeness in overall harmonic structure.