|
|
Automated compression of neural network weights
Lorinc, Marián ; Sekanina, Lukáš (referee) ; Mrázek, Vojtěch (advisor)
Konvolučné neurónové siete (CNN) od svojho vynájdenia zrevolucionizovali spôsob, akým sa realizujú úlohy z odvetvia počítačového videnia. Vynález CNN viedol k zníženiu pamäťovej náročnosti, keďže váhy boli nahradené konvolučnými filtrami obsahujúcimi menej trénovateľných váh. Avšak, toto zníženie bolo dosiahnuté na úkor zvýšenia požiadaviek na výpočtový výkon, ktorý je naviazaný na výpočet konvolúcie. Táto práca skúma hypotézu, či je možné sa vyhnúť načítavaniu váh a miesto toho ich vypočítať, čím sa ušetrí energia. Na otestovanie tejto hypotézy bol vyvinutý nový algoritmus kompresie váh využívajúci Kartézske genetické programovanie. Tento algoritmus hľadá najoptimálnejšiu funkciu kompresie váh s cieľom zvýšiť energetickú účinnosť. Experimenty vykonané na architektúrach LeNet-5 a MobileNetV2 ukázali, že algoritmus dokáže efektívne znížiť spotrebu energie pri zachovaní vysokej presnosti modelu. Výsledky ukázali, že určité vrstvy je možné doplniť vypočítanými váhami, čo potvrdzuje potenciál pre energeticky efektívne neurónové siete.
|
|
|
Evolutionary Design of Image Classifier
Koči, Martin ; Bidlo, Michal (referee) ; Drahošová, Michaela (advisor)
This thesis deals with evolutionary design of image classifier with help of genetic programming, specifically with cartesian genetic programming. Thesis discribes teoretical basics of machine learing, evolutionary algorithms and genetic programming. Part of this thesis is described design of the program and its implementation. Futhermore, experiments are performed on two solved tasks for the classification of handwritten digits and the classification of cube drawings, which can be used to determine the rate of dementia in Parkinson's disease. The best designed solution for digits is with AUC of 0.95 and for cubes 0.86. Designed solutions are compared by other methods, namely convolutional neural networks (CNN) and the support vector machines (SVM). The resulting AUC for the classification of digits for both CNN and SVM is 0.99, for cubes CNN has a final AUC 0.81 and SVM 0.69. The cubes are then compared with existing solution, which resulted in AUC 0.70, so that the results of the experiments show an improvement in the method used in this thesis.
|
|
|
Polymorphic Self-Checking Circuits
Mazuch, Martin ; Růžička, Richard (referee) ; Sekanina, Lukáš (advisor)
This Master's thesis deals with question of the development of self-checking polymorphic circuits. It deals with a traditional way of creating reliable and self-checking circuits, presenting basic principles and methods. Also a method of Cartesian Genetic Programming for development of combinational circuits is explained. This thesis describes concepts of polymorphic gates and circuits and their benefits in practical use. Some existing self-checking polymorphic circuits are presented and their self-checking capabilities are analyzed. A proposal of realization of a design system for self-checking polymorphic circuits is given. A design system has been built based on presented specification and an application allowing simulations and analysis of system-proposed solutions has been created. Variety of experiments have been performed at created system and several interesting solutions have been acquired. At the end, conclusion is given and benefits of MSc. project are discussed.
|
|
|
Evolutionary Design of Image Classifier
Koči, Martin ; Bidlo, Michal (referee) ; Drahošová, Michaela (advisor)
This thesis deals with evolutionary design of image classifier with help of genetic programming, specifically with cartesian genetic programming. Thesis discribes teoretical basics of machine learing, evolutionary algorithms and genetic programming. Part of this thesis is described design of the program and its implementation. Futhermore, experiments are performed on two solved tasks for the classification of handwritten digits and the classification of cube drawings, which can be used to determine the rate of dementia in Parkinson's disease. The best designed solution for digits is with AUC of 0.95 and for cubes 0.86. Designed solutions are compared by other methods, namely convolutional neural networks (CNN) and the support vector machines (SVM). The resulting AUC for the classification of digits for both CNN and SVM is 0.99, for cubes CNN has a final AUC 0.81 and SVM 0.69. The cubes are then compared with existing solution, which resulted in AUC 0.70, so that the results of the experiments show an improvement in the method used in this thesis.
|
|
|
Polymorphic Self-Checking Circuits
Mazuch, Martin ; Růžička, Richard (referee) ; Sekanina, Lukáš (advisor)
This Master's thesis deals with question of the development of self-checking polymorphic circuits. It deals with a traditional way of creating reliable and self-checking circuits, presenting basic principles and methods. Also a method of Cartesian Genetic Programming for development of combinational circuits is explained. This thesis describes concepts of polymorphic gates and circuits and their benefits in practical use. Some existing self-checking polymorphic circuits are presented and their self-checking capabilities are analyzed. A proposal of realization of a design system for self-checking polymorphic circuits is given. A design system has been built based on presented specification and an application allowing simulations and analysis of system-proposed solutions has been created. Variety of experiments have been performed at created system and several interesting solutions have been acquired. At the end, conclusion is given and benefits of MSc. project are discussed.
|
guest ::
