|
|
Hash Function Design Using Genetic Programming
Michalisko, Tomáš ; Piňos, Michal (referee) ; Sekanina, Lukáš (advisor)
This thesis deals with automated design of hash functions using Cartesian genetic programming. The chosen method for collision resolution is cuckoo hashing. Three variants of hash function encodings were compared. Experiments were performed with datasets containing network flows. The most suitable parameters of CGP, including the function set, were determined. The best evolved hash functions achieved comparable results to the functions designed by experts. The main finding is that hash functions consisting of 64-bit operations achieve the best results.
|
|
|
Radar-Based Measurement for Speed Disciplines
Piňos, Michal ; Široký, Adam (referee) ; Maršík, Lukáš (advisor)
The aim of this bachelor thesis is radar-based measurement for speed disciplines. For this purpose, the Doppler radar with continuous wave was used, K-MC4 to be specific. Standard signal processing techniques were used to extract the speed information from the radar signal. The key method for obtaining Doppler frequency from signal is Fourier transform. Cosine effect is compensated based on the computed angle.The result of this work is a detector capable of measuring speed and direction of measured objects. Implemented solution also allows the detection of certain objects.
|
|
|
The Study of Order Processing Through Enterprise
Farníková, Jana ; Piňoš, Michal (referee) ; Jurová, Marie (advisor)
This thesis focusses on how a specific order is processed in a specific company. The analysis is more specifically focussed on heat meters, which make up a substantial part of the company sales. It contains suggestions on how the company could process these orders using a program called Microsoft Project, which could benefit the company in many respects.
|
|
|
Evolutionary Design of Convolutional Neural Networks
Piňos, Michal ; Vašíček, Zdeněk (referee) ; Sekanina, Lukáš (advisor)
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.
|
|
|
Prediktory přesnosti konvolučních neuronových sítí
Karásek, Daniel ; Mrázek, Vojtěch (referee) ; Piňos, Michal (advisor)
V posledním desetiletí došlo k obrovskému skoku v pokroku neuronových sítí, a to především díky možnosti učit větší sítě než kdy dřív. Pouhé zvětšování velikosti sítí ale není dostatečným prostředkem k jejich dalšímu zefektivnění. Z tohoto důvodu dochází ke komplexnějšímu výzkumu architektur sítí. Jeho velkou slabinou je potřeba natrénovat každou architekturu pro zjištění jejího výkonu na daném problému. To může v některých případech zabírat i dny. Alternativou k učení může být využití prediktoru přesnosti neuronové sítě. Tato práce se zabývá zhodnocením a reimplementací několika vybraných prediktorů určených pro klasifikační konvoluční sítě.
|
|
|
Differentiable Neural Network Architecture Search
Eichler, Vojtěch ; Piňos, Michal (referee) ; Mrázek, Vojtěch (advisor)
The aim of this work is to propose a system for differentiable architecture search, which can be used for design of some neural network types. The work is based on the DARTS (Differentiable architecture search) approach and implements similar system in TensorFlow. Experiments with regular convolution neural networks, convolution neural networks using approximate multipliers and neural networks combining attention and convolution machanisms are presented. The main contribution of this work is novel implementation of a diferentiable architecture search system supporting various layers from the recent versions of the TensorFlow library.
|
|
|
Hash Function Design Using Genetic Programming
Michalisko, Tomáš ; Piňos, Michal (referee) ; Sekanina, Lukáš (advisor)
This thesis deals with automated design of hash functions using Cartesian genetic programming. The chosen method for collision resolution is cuckoo hashing. Three variants of hash function encodings were compared. Experiments were performed with datasets containing network flows. The most suitable parameters of CGP, including the function set, were determined. The best evolved hash functions achieved comparable results to the functions designed by experts. The main finding is that hash functions consisting of 64-bit operations achieve the best results.
|
|
|
Evolutionary Design of Convolutional Neural Networks
Piňos, Michal ; Vašíček, Zdeněk (referee) ; Sekanina, Lukáš (advisor)
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.
|
|
|
Radar-Based Measurement for Speed Disciplines
Piňos, Michal ; Široký, Adam (referee) ; Maršík, Lukáš (advisor)
The aim of this bachelor thesis is radar-based measurement for speed disciplines. For this purpose, the Doppler radar with continuous wave was used, K-MC4 to be specific. Standard signal processing techniques were used to extract the speed information from the radar signal. The key method for obtaining Doppler frequency from signal is Fourier transform. Cosine effect is compensated based on the computed angle.The result of this work is a detector capable of measuring speed and direction of measured objects. Implemented solution also allows the detection of certain objects.
|
|
|
The Study of Order Processing Through Enterprise
Farníková, Jana ; Piňoš, Michal (referee) ; Jurová, Marie (advisor)
This thesis focusses on how a specific order is processed in a specific company. The analysis is more specifically focussed on heat meters, which make up a substantial part of the company sales. It contains suggestions on how the company could process these orders using a program called Microsoft Project, which could benefit the company in many respects.
|
guest ::
