|
|
GPU-Accelerated Synthesis of Probabilistic Programs
Marcin, Vladimír ; Matyáš, Jiří (referee) ; Češka, Milan (advisor)
V tejto práci sa zoberáme problémom automatizovanej syntézy pravdepodobnostných programov: majme konečnú rodinu kandidátnych programov, v ktorej chceme efektívne identifikovať program spĺňajúci danú špecifikáciu. Aj riešenie tých najjednoduchších syntéznych problémov v praxi predstavuje NP-ťažký problém. Pokrok v tejto oblasti prináša nástroj Paynt, ktorý na riešenie tohto problému používa novú integrovanú metódu syntézy pravdepodobnostných programov. Aj keď sa tento prístup dokáže efektívne vysporiadať s exponenciálnym rastom rodín kandidátnych riešení, stále tu existuje problém spôsobený exponenciálnym rastom jednotlivých členov týchto rodín. S cieľom vysporiadať sa aj s týmto problémom, sme implementovali GPU orientované algoritmy slúžiace na overovanie kandidátnych programov (modelov), ktoré danú úlohu paralelizujú na stavovej úrovni pravdepodobnostých modelov. Celkové zrýchlenie doshiahnuté týmto prístupom za určitých podmienok potom prinieslo takmer teoretický limit možného zrýchlenia syntézneho procesu.
|
|
|
Parallelization and Optimization of Image Processing Applications
Šiška, Jakub ; Seeman, Michal (referee) ; Černocký, Jan (advisor)
This Bachelor's Thesis was performed during a study stay at the École Supérieure d'Ingénieurs en Électronique et Électrotechnique Paris, France. It proposes solution for speeding up image processing algorithm and its adoption for use with real-time video stream from the infra red camera. The first part discusses characteristics and basic principles of the IR technology, followed by specifications of used camera. Ongoing text also proposes solution of problems concerning network communication with the camera. In addition, it describes camera's output stream format characteristics and solution for output visualisation. Substantial part of this work covers issues concerning parallelization and optimization of video stream and image file data processing. Problem of the parallelisation for this case is explained together with implemented parallelization method. Entire theoretical part is supported with the real results, benchmarks, which are presented in the last chapter.
|
|
|
Parallel genetic algorithm
Trupl, Jan ; Kobliha, Miloš (referee) ; Jaroš, Jiří (advisor)
The thesis describes design and implementation of various evolutionary algorithms, which were enhanced to use the advantages of parallelism on the multiprocessor systems along with ability to run the computation on different machines in a computer network. The purpose of these algorithms is to find the global extreme of function of $n$ variables. In the thesis, there are demonstrated various optimization problems, and their effective solution with the help of evolutionary algorithms. There are also described interface libraries MPI(Message Passing Interface) and OpenMP, in the extent needed to understand the problematic of parallel evolutionary algorithms.
|
|
|
Parallel Evolutionary Algorithm EDA Based on Copulas
Hyrš, Martin ; Brandejský, Tomáš (referee) ; Matoušek, Radomil (referee) ; Schwarz, Josef (advisor)
In my thesis I~ deal with the design, implementation and testing of the advanced parallel Estimation of Distribution Algorithm (EDA) utilizing copula theory to create a~ probabilistic model. A~new population is created by the process of sampling the joint distribution function, which models the current distribution of the subpopulation of promising individuals . The usage of copulas increases the efficiency of the learning process and sampling the probabilistic model. It can be separated into mutually independent marginal distributions and the copula , which represents the correlations between the variables of the solved problem. This concept initiated the usage of the parallel island architecture , in which the migration of probabilistic models belonging to individual islands ' subpopulations was used instead of the migration of individuals . The statistical tests used in the comparison of the proposed algorithm ( mCEDA = migrating Copula - based Estimation of Distribution Algorithm ) and the algorithms of other authors confirmed the effectiveness of the proposed concept .
|
|
|
Parallel Evolutionary Algorithm EDA Based on Copulas
Hyrš, Martin ; Brandejský, Tomáš (referee) ; Matoušek, Radomil (referee) ; Schwarz, Josef (advisor)
In my thesis I~ deal with the design, implementation and testing of the advanced parallel Estimation of Distribution Algorithm (EDA) utilizing copula theory to create a~ probabilistic model. A~new population is created by the process of sampling the joint distribution function, which models the current distribution of the subpopulation of promising individuals . The usage of copulas increases the efficiency of the learning process and sampling the probabilistic model. It can be separated into mutually independent marginal distributions and the copula , which represents the correlations between the variables of the solved problem. This concept initiated the usage of the parallel island architecture , in which the migration of probabilistic models belonging to individual islands ' subpopulations was used instead of the migration of individuals . The statistical tests used in the comparison of the proposed algorithm ( mCEDA = migrating Copula - based Estimation of Distribution Algorithm ) and the algorithms of other authors confirmed the effectiveness of the proposed concept .
|
|
|
GPU-Accelerated Synthesis of Probabilistic Programs
Marcin, Vladimír ; Matyáš, Jiří (referee) ; Češka, Milan (advisor)
V tejto práci sa zoberáme problémom automatizovanej syntézy pravdepodobnostných programov: majme konečnú rodinu kandidátnych programov, v ktorej chceme efektívne identifikovať program spĺňajúci danú špecifikáciu. Aj riešenie tých najjednoduchších syntéznych problémov v praxi predstavuje NP-ťažký problém. Pokrok v tejto oblasti prináša nástroj Paynt, ktorý na riešenie tohto problému používa novú integrovanú metódu syntézy pravdepodobnostných programov. Aj keď sa tento prístup dokáže efektívne vysporiadať s exponenciálnym rastom rodín kandidátnych riešení, stále tu existuje problém spôsobený exponenciálnym rastom jednotlivých členov týchto rodín. S cieľom vysporiadať sa aj s týmto problémom, sme implementovali GPU orientované algoritmy slúžiace na overovanie kandidátnych programov (modelov), ktoré danú úlohu paralelizujú na stavovej úrovni pravdepodobnostých modelov. Celkové zrýchlenie doshiahnuté týmto prístupom za určitých podmienok potom prinieslo takmer teoretický limit možného zrýchlenia syntézneho procesu.
|
|
|
Parallel genetic algorithm
Trupl, Jan ; Kobliha, Miloš (referee) ; Jaroš, Jiří (advisor)
The thesis describes design and implementation of various evolutionary algorithms, which were enhanced to use the advantages of parallelism on the multiprocessor systems along with ability to run the computation on different machines in a computer network. The purpose of these algorithms is to find the global extreme of function of $n$ variables. In the thesis, there are demonstrated various optimization problems, and their effective solution with the help of evolutionary algorithms. There are also described interface libraries MPI(Message Passing Interface) and OpenMP, in the extent needed to understand the problematic of parallel evolutionary algorithms.
|
|
|
Parallelization and Optimization of Image Processing Applications
Šiška, Jakub ; Seeman, Michal (referee) ; Černocký, Jan (advisor)
This Bachelor's Thesis was performed during a study stay at the École Supérieure d'Ingénieurs en Électronique et Électrotechnique Paris, France. It proposes solution for speeding up image processing algorithm and its adoption for use with real-time video stream from the infra red camera. The first part discusses characteristics and basic principles of the IR technology, followed by specifications of used camera. Ongoing text also proposes solution of problems concerning network communication with the camera. In addition, it describes camera's output stream format characteristics and solution for output visualisation. Substantial part of this work covers issues concerning parallelization and optimization of video stream and image file data processing. Problem of the parallelisation for this case is explained together with implemented parallelization method. Entire theoretical part is supported with the real results, benchmarks, which are presented in the last chapter.
|
|
| |
guest ::
