Essays about: "classification robustness"
Showing result 11 - 15 of 55 essays containing the words classification robustness.
-
11. Brightest Cluster Galaxies in the Local Universe: Mergers, Interactions and the Implications for Galaxy Evolution
University essay from Luleå tekniska universitet/RymdteknikAbstract : Clusters of Galaxies are amongst the largest gravitationally bound structures in our Universe and consist of thousands of galaxies. It is in these gigantic systems where Brightest Cluster Galaxies (BCGs) are found, the most massive galaxies in our Universe. A BCG, as its name indicates, is the brightest galaxy in a cluster. READ MORE
-
12. Improving the Robustness of Deep Neural Networks against Adversarial Examples via Adversarial Training with Maximal Coding Rate Reduction
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Deep learning is one of the hottest scientific topics at the moment. Deep convolutional networks can solve various complex tasks in the field of image processing. However, adversarial attacks have been shown to have the ability of fooling deep learning models. READ MORE
-
13. Data Complexity and its effect on Classification Accuracy in Multi Class Classification Problems : A study using synthetic datasets
University essay from KTH/DatavetenskapAbstract : This study investigates how the performance of a selection of machine learning classifiers is affected by the data complexity, measured by F1, N1, N2, and N3 in a multi class classification setting. This study uses synthetic datasets that span across the range of possible complexity levels for each complexity measure, allowing us to target the desired level of complexity for each dataset. READ MORE
-
14. Deep neural network for object classification and optimization algorithms for 3D positioning in Ultrasonic Sensor Array
University essay from Umeå universitet/Institutionen för datavetenskapAbstract : Ultrasonic sensors are commonly used in automobiles to assist driving maneuvers, e.g., parking, because of their cost-effectiveness and robustness. READ MORE
-
15. Evaluating Robustness of a CNN Architecture introduced to the Adversarial Attacks
University essay from Blekinge Tekniska HögskolaAbstract : Abstract: Background: From Previous research, state-of-the-art deep neural networks have accomplished impressive results on many images classification tasks. However, adversarial attacks can easily fool these deep neural networks by adding little noise to the input images. READ MORE