|
Visual Simulator and Debugger of Neural Networks
Beluský, Ondrej ; Zbořil, František (referee) ; Martinek, David (advisor)
Artificial neural networks represent computational parallel systems. This part of artificial intelligence is still researched. Basically neural network is the set of neurons, which are connected together. These networks have aspects of human intelligence, because they have an ability to learn. Their main goal is to simulate human brain, but creating such a network with large number of neurons and connections between them is impossible. They simulate some parts of human thinking. My task was to create visual simulator and debugger of these networks. The program was supposed to have a choice to debugging and stepping the algorithm for learning. My goal was also to implement editor, which allows creating and editing neural networks.
|
|
Abstract Syntax Tree Analysis for Python Teaching Support
Fáber, Jakub ; Škoda, Petr (referee) ; Smrž, Pavel (advisor)
The goal of this thesis is to create an analyzer system to check assignment solutions and to suggest improvements for them in terms of code quality and cleanliness. For the best results, a combination of static and dynamic analysis techniques is used. This system is implemented in the form of tutoring system and uses Docker containers for safe testing and analysis in an isolated environment. Interactive environment for communication with users is created with modern technologies such as Material Design.
|
|
Abstract Syntax Tree Analysis for Python Teaching Support
Fáber, Jakub ; Škoda, Petr (referee) ; Smrž, Pavel (advisor)
The goal of this thesis is to create an analyzer system to check assignment solutions and to suggest improvements for them in terms of code quality and cleanliness. For the best results, a combination of static and dynamic analysis techniques is used. This system is implemented in the form of tutoring system and uses Docker containers for safe testing and analysis in an isolated environment. Interactive environment for communication with users is created with modern technologies such as Material Design.
|
|
Visual Simulator and Debugger of Neural Networks
Beluský, Ondrej ; Zbořil, František (referee) ; Martinek, David (advisor)
Artificial neural networks represent computational parallel systems. This part of artificial intelligence is still researched. Basically neural network is the set of neurons, which are connected together. These networks have aspects of human intelligence, because they have an ability to learn. Their main goal is to simulate human brain, but creating such a network with large number of neurons and connections between them is impossible. They simulate some parts of human thinking. My task was to create visual simulator and debugger of these networks. The program was supposed to have a choice to debugging and stepping the algorithm for learning. My goal was also to implement editor, which allows creating and editing neural networks.
|