|
|
Evolutionary Algorithms in Convolutional Neural Network Design
Badáň, Filip ; Vašíček, Zdeněk (referee) ; Sekanina, Lukáš (advisor)
This work focuses on automatization of neural network design via the so-called neuroevolution, which employs evolutionary algorithms to construct artificial neural networks or optimise their parameters. The goal of the project is to design and implement an evolutionary algorithm which can be used in the process of designing and optimizing topologies of convolutional neural networks. The effectiveness of the proposed framework was experimentally evaluated on tasks of image classification on datasets MNIST and CIFAR10 and compared with relevant solutions. The results showed that neuroevolution has a potential to successfully find accurate and effective convolutional neural network architectures.
|
|
|
ASIPs Intelligent Testbench Automation
Badáň, Filip ; Hynek, Jiří (referee) ; Zachariášová, Marcela (advisor)
This thesis focuses on the proposal and implementation of intelligent testbench automation for application-specific processors. The main goal of the thesis is to connect UVM verification environment with already designed genetic algorithm and to prepare this verification environment for integration into Codasip Studio development environment. The core of the final solution is modification of UVM components in verification environment and communication between the genetic algorithm and the generator of random test applications.
|
|
|
Evolutionary Algorithms in Convolutional Neural Network Design
Badáň, Filip ; Vašíček, Zdeněk (referee) ; Sekanina, Lukáš (advisor)
This work focuses on automatization of neural network design via the so-called neuroevolution, which employs evolutionary algorithms to construct artificial neural networks or optimise their parameters. The goal of the project is to design and implement an evolutionary algorithm which can be used in the process of designing and optimizing topologies of convolutional neural networks. The effectiveness of the proposed framework was experimentally evaluated on tasks of image classification on datasets MNIST and CIFAR10 and compared with relevant solutions. The results showed that neuroevolution has a potential to successfully find accurate and effective convolutional neural network architectures.
|
|
|
ASIPs Intelligent Testbench Automation
Badáň, Filip ; Hynek, Jiří (referee) ; Zachariášová, Marcela (advisor)
This thesis focuses on the proposal and implementation of intelligent testbench automation for application-specific processors. The main goal of the thesis is to connect UVM verification environment with already designed genetic algorithm and to prepare this verification environment for integration into Codasip Studio development environment. The core of the final solution is modification of UVM components in verification environment and communication between the genetic algorithm and the generator of random test applications.
|
guest ::
