Thesis Details
Evoluční návrh konvolučních neuronových sítí
The aim of this work is to design and implement a program for automated design of convolutional neural networks (CNN) with the use of evolutionary computing techniques. From a practical point of view, this approach reduces the requirements for the human factor in the design of CNN architectures, and thus eliminates the tedious and laborious process of manual design. This work utilizes a special form of genetic programming, called Cartesian genetic programming, which uses a graph representation for candidate solution encoding.This technique enables the user to parameterize the CNN search process and focus on architectures, that are interesting from the view of used computational units, accuracy or number of parameters. The proposed approach was tested on the standardized CIFAR-10dataset, which is often used by researchers to compare the performance of their CNNs. The performed experiments showed, that this approach has both research and practical potential and the implemented program opens up new possibilities in automated CNN design.
convolutional neural networks, evolutionary algorithms, cartesian genetic programming, neuroevolution
Čadík Martin, doc. Ing., Ph.D. (DCGM FIT BUT), člen
Lengál Ondřej, Ing., Ph.D. (DITS FIT BUT), člen
Malinka Kamil, Mgr., Ph.D. (DITS FIT BUT), člen
Polčák Libor, Ing., Ph.D. (DIFS FIT BUT), člen
Veselý Vladimír, Ing., Ph.D. (DIFS FIT BUT), člen
@mastersthesis{FITMT21369, author = "Michal Pi\v{n}os", type = "Master's thesis", title = "Evolu\v{c}n\'{i} n\'{a}vrh konvolu\v{c}n\'{i}ch neuronov\'{y}ch s\'{i}t\'{i}", school = "Brno University of Technology, Faculty of Information Technology", year = 2020, location = "Brno, CZ", language = "czech", url = "https://www.fit.vut.cz/study/thesis/21369/" }