|
|
Detekce malware domén pomocí metod strojového učení
Ebert, Tomáš ; Poliakov, Daniel (referee) ; Hranický, Radek (advisor)
This bachelor thesis deals with the detection of malware domains using machine learning methods learning based on various information obtained about the domain (DNS records, geolocation data etc.). With the rapid proliferation of threats, not only in the form of malware, the current examples are often approaches are insufficient, either in terms of the speed of detection of malware domains or in terms of overall recognition,whether a domain is dangerous. The output of this work is a trained XGBoost classifier model, which has the advantage of fast and efficient real-time detection over blacklist detection, which often acquires domain data with a week delay. For this model, 131,000 malware domains were obtained, using which obtain a high-value model. Using experiments, a score of F1 of 96.8786 % for the XGBoost classifier with a false positive detection rate of 0.004887.
|
|
|
Machine Learning in Strategic Games
Vlček, Michael ; Škoda, Petr (referee) ; Smrž, Pavel (advisor)
Machine learning is spearheading progress for the field of artificial intelligence in terms of providing competition in strategy games to a human opponent, be it in a game of chess, Go or poker. A field of machine learning, which shows the most promising results in playing strategy games, is reinforcement learning. The next milestone for the current research lies in a computer game Starcraft II, which outgrows the previous ones in terms of complexity, and represents a potential new breakthrough in this field. The paper focuses on analysis of the problem, and suggests a solution incorporating a reinforcement learning algorithm A2C and hyperparameter optimization implementation PBT, which could mean a step forward for the current progress.
|
|
|
Optimizing neural network architecture for EEG processing using evolutionary algorithms
Pijáčková, Kristýna ; Maršálek, Roman (referee) ; Götthans, Tomáš (advisor)
Tato práce se zabývá optimalizací hyperparametrů neuronových sítí pro zpracování EEG signálu pomocí evolučních algoritmů. Využití evolučních optimalizace může snížit závislost na lidské intuici a empirických znalostech při návrhu neuronové sítě a může tak zefektivnit návrh neuronové sítě. V této práci byl navržen genetický algoritmus, který je vhodný pro optimalizaci hyperparametrů i pro hledání neuronové architektury. Tyto metody byly porovnány s referenčním modelem navrženým inženýrem s expertýzou v této oblasti. Data použitá v této práci jsou rozdělena do čtyř kategorií a pocházejí z Fakultní nemocnice svaté Anny v Brně (SAUH) a Mayo kliniky (MAYO) a obsahují iEEG záznamy u pacienta s epilepsií rezistentní na léky, který podstupuje předoperační vyšetření. Metoda hledání neuronové architektury dosáhla výsledků srovnatelných s referenčním modelem. Optimalizovaný model zlepšil F1 skóre oproti originálnímu, empiricky navrženému modelu z 0.9076 na 0.9673 pro data z SAUH a 0.9222 na 0.9400 pro data z Mayo kliniky. Ke zvýšenému skóre přispěla hlavně zvýšená přesnost klasifikace patologických událostí a šumu, která může mít dále pozitivní vliv v aplikacích tohoto modelu v detektoru záchvatů a šumu.
|
|
|
Hyperparameter optimization in AutoML systems
Pešková, Klára ; Neruda, Roman (advisor) ; Awad, Mariette (referee) ; Kordik, Pavel (referee)
In the last few years, as processing the data became a part of everyday life in different areas of human activity, the automated machine learning systems that are designed to help with the process of data mining, are on the rise. Various metalearning techniques, including recommendation of the right method to use, or the sequence of steps to take, and to find its optimum hyperparameters configuration, are integrated into these systems to help the researchers with the machine learning tasks. In this thesis, we proposed metalearning algorithms and techniques for hyperparameters optimization, narrowing the intervals of hyperparameters, and recommendations of a machine learning method for a never before seen dataset. We designed two AutoML machine learning systems, where these metalearning techniques are implemented. The extensive set of experiments was proposed to evaluate these algorithms, and the results are presented.
|
|
|
Hyperparameter optimization in AutoML systems
Pešková, Klára ; Neruda, Roman (advisor) ; Awad, Mariette (referee) ; Kordik, Pavel (referee)
In the last few years, as processing the data became a part of everyday life in different areas of human activity, the automated machine learning systems that are designed to help with the process of data mining, are on the rise. Various metalearning techniques, including recommendation of the right method to use, or the sequence of steps to take, and to find its optimum hyperparameters configuration, are integrated into these systems to help the researchers with the machine learning tasks. In this thesis, we proposed metalearning algorithms and techniques for hyperparameters optimization, narrowing the intervals of hyperparameters, and recommendations of a machine learning method for a never before seen dataset. We designed two AutoML machine learning systems, where these metalearning techniques are implemented. The extensive set of experiments was proposed to evaluate these algorithms, and the results are presented.
|
|
|
Machine Learning in Strategic Games
Vlček, Michael ; Škoda, Petr (referee) ; Smrž, Pavel (advisor)
Machine learning is spearheading progress for the field of artificial intelligence in terms of providing competition in strategy games to a human opponent, be it in a game of chess, Go or poker. A field of machine learning, which shows the most promising results in playing strategy games, is reinforcement learning. The next milestone for the current research lies in a computer game Starcraft II, which outgrows the previous ones in terms of complexity, and represents a potential new breakthrough in this field. The paper focuses on analysis of the problem, and suggests a solution incorporating a reinforcement learning algorithm A2C and hyperparameter optimization implementation PBT, which could mean a step forward for the current progress.
|
guest ::
